https://vasp.at/wiki/index.php?action=history&feed=atom&title=ML_CX 2026-04-15T20:23:00Z Revision history for this page on the wiki MediaWiki 1.43.8 https://vasp.at/wiki/index.php?title=ML_CX&diff=25140&oldid=prev 2024-06-12T12:26:50Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 12:26, 12 June 2024</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l6">Line 6:</td> <td colspan="2" class="diff-lineno">Line 6:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The use of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the <del style="font-weight: bold; text-decoration: none;">Bayesian </del>errors of the forces stored in a history. Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data. In the first case the average is performed over <del style="font-weight: bold; text-decoration: none;">Bayesian </del>errors after updates of the force fields, and in the second case over all recent <del style="font-weight: bold; text-decoration: none;">Bayesian </del>error estimates (see {{TAG|ML_ICRITERIA}}). In both cases, if {{TAG|ML_CTIFOR}} is updated, it is set to  </div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the errors of the forces stored in a history. Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data. In the first case the average is performed over errors after updates of the force fields, and in the second case over all recent error estimates (see {{TAG|ML_ICRITERIA}}). In both cases, if {{TAG|ML_CTIFOR}} is updated, it is set to  </div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored <del style="font-weight: bold; text-decoration: none;">Bayesian </del>errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 for {{TAG|ML_ICRITERIA}}=1, and 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 (a good starting value is 0.2 for {{TAG|ML_ICRITERIA}}=2). For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 for {{TAG|ML_ICRITERIA}}=1, and 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 (a good starting value is 0.2 for {{TAG|ML_ICRITERIA}}=2). For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td></tr> </table>

Karsai https://vasp.at/wiki/index.php?title=ML_CX&diff=18996&oldid=prev 2022-09-17T15:24:23Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 15:24, 17 September 2022</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l2">Line 2:</td> <td colspan="2" class="diff-lineno">Line 2:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAGDEF|ML_CX|[real]|0.0}}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAGDEF|ML_CX|[real]|0.0}}</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Description: The parameter determines <del style="font-weight: bold; text-decoration: none;">how </del>the <del style="font-weight: bold; text-decoration: none;"> </del>threshold  ({{TAG|ML_CTIFOR}}) is updated within the machine learning force field methods.</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>Description: The parameter determines <ins style="font-weight: bold; text-decoration: none;">to which value </ins>the threshold  ({{TAG|ML_CTIFOR}}) is updated within the machine learning force field methods.</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>----</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>----</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>The <del style="font-weight: bold; text-decoration: none;">usage </del>of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>The <ins style="font-weight: bold; text-decoration: none;">use </ins>of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in a history. Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data. In the first case the average is performed over Bayesian errors after updates of the force fields, and in the second case over all Bayesian error estimates (see {{TAG|ML_ICRITERIA}}). In both cases, if {{TAG|ML_CTIFOR}} is updated, it is set to  </div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in a history. Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data. In the first case the average is performed over Bayesian errors after updates of the force fields, and in the second case over all <ins style="font-weight: bold; text-decoration: none;">recent </ins>Bayesian error estimates (see {{TAG|ML_ICRITERIA}}). In both cases, if {{TAG|ML_CTIFOR}} is updated, it is set to  </div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td></tr> <tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l12">Line 12:</td> <td colspan="2" class="diff-lineno">Line 12:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 for {{TAG|ML_ICRITERIA}}=1, and 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 (a good starting value is 0.2 for {{TAG|ML_ICRITERIA}}=2). For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 for {{TAG|ML_ICRITERIA}}=1, and 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 (a good starting value is 0.2 for {{TAG|ML_ICRITERIA}}=2). For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2 (in future releases 50 x {{TAG|ML_MHIS}}).</div></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>(in future releases 50 x {{TAG|ML_MHIS}}).</div></td><td colspan="2" class="diff-side-added"></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Related tags and articles ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Related tags and articles ==</div></td></tr> </table>

Kresse https://vasp.at/wiki/index.php?title=ML_CX&diff=18994&oldid=prev 2022-09-17T15:20:07Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 15:20, 17 September 2022</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l12">Line 12:</td> <td colspan="2" class="diff-lineno">Line 12:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 for {{TAG|ML_ICRITERIA}}=1, and 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 (a good starting value is 0.2 for {{TAG|ML_ICRITERIA}}=2). For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 for {{TAG|ML_ICRITERIA}}=1, and 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 (a good starting value is 0.2 for {{TAG|ML_ICRITERIA}}=2). For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2.</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2</div></td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">(in future releases 50 x {{TAG|ML_MHIS}})</ins>.</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Related tags and articles ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Related tags and articles ==</div></td></tr> </table>

Kresse https://vasp.at/wiki/index.php?title=ML_CX&diff=18988&oldid=prev 2022-09-17T10:04:56Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 10:04, 17 September 2022</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l10">Line 10:</td> <td colspan="2" class="diff-lineno">Line 10:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 for {{TAG|ML_ICRITERIA}}=1 and<del style="font-weight: bold; text-decoration: none;">, </del>0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 (a good starting value is 0.<del style="font-weight: bold; text-decoration: none;">15 </del>for {{TAG|ML_ICRITERIA}}=2). For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 for {{TAG|ML_ICRITERIA}}=1<ins style="font-weight: bold; text-decoration: none;">, </ins>and 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 (a good starting value is 0.<ins style="font-weight: bold; text-decoration: none;">2 </ins>for {{TAG|ML_ICRITERIA}}=2). For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2.</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2.</div></td></tr> </table>

Kresse https://vasp.at/wiki/index.php?title=ML_CX&diff=18987&oldid=prev 2022-09-17T09:55:27Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 09:55, 17 September 2022</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l6">Line 6:</td> <td colspan="2" class="diff-lineno">Line 6:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history. Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data. In the first case the average is performed over Bayesian errors after updates of the force fields, and the second case over all Bayesian error estimates (see {{TAG|ML_ICRITERIA}}). In both cases, if {{TAG|ML_CTIFOR}} is updated, it is set to  </div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in <ins style="font-weight: bold; text-decoration: none;">a </ins>history. Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data. In the first case the average is performed over Bayesian errors after updates of the force fields, and <ins style="font-weight: bold; text-decoration: none;">in </ins>the second case over all Bayesian error estimates (see {{TAG|ML_ICRITERIA}}). In both cases, if {{TAG|ML_CTIFOR}} is updated, it is set to  </div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 {{TAG|ML_ICRITERIA}}=1 and, 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2. For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.2 and 0.0 <ins style="font-weight: bold; text-decoration: none;">for </ins>{{TAG|ML_ICRITERIA}}=1 and, 0.0 and 0.3 for {{TAG|ML_ICRITERIA}}=2 <ins style="font-weight: bold; text-decoration: none;">(a good starting value is 0.15 for {{TAG|ML_ICRITERIA}}=2)</ins>. For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2.</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2.</div></td></tr> </table>

Kresse https://vasp.at/wiki/index.php?title=ML_CX&diff=18986&oldid=prev 2022-09-17T09:53:00Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 09:53, 17 September 2022</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l6">Line 6:</td> <td colspan="2" class="diff-lineno">Line 6:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history . Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data<del style="font-weight: bold; text-decoration: none;">, in </del>the first case over Bayesian errors after updates of the force fields, and the second case<del style="font-weight: bold; text-decoration: none;">, </del>over all Bayesian <del style="font-weight: bold; text-decoration: none;">errors </del>(see {{TAG|ML_ICRITERIA}}). In both cases, if {{TAG|ML_CTIFOR}} is updated, it is set to  </div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history. Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data<ins style="font-weight: bold; text-decoration: none;">. In </ins>the first case <ins style="font-weight: bold; text-decoration: none;">the average is performed </ins>over Bayesian errors after updates of the force fields, and the second case over all Bayesian <ins style="font-weight: bold; text-decoration: none;">error estimates </ins>(see {{TAG|ML_ICRITERIA}}). In both cases, if {{TAG|ML_CTIFOR}} is updated, it is set to  </div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td></tr> </table>

Kresse https://vasp.at/wiki/index.php?title=ML_CX&diff=18985&oldid=prev 2022-09-17T09:51:49Z

<p>ML_ICRITERIA=2 explained in more detail.</p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 09:51, 17 September 2022</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l6">Line 6:</td> <td colspan="2" class="diff-lineno">Line 6:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The usage of this tag in combination with the learning algorithms is described here: [[Machine learning force field calculations: Basics#Threshold for error of forces|here]].</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history (see {{TAG|ML_ICRITERIA}}), <del style="font-weight: bold; text-decoration: none;">specifically</del>,</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history <ins style="font-weight: bold; text-decoration: none;">. Note that {{TAG|ML_ICRITERIA}}=1 and {{TAG|ML_ICRITERIA}}=2, average over different data, in the first case over Bayesian errors after updates of the force fields, and the second case, over all Bayesian errors </ins>(see {{TAG|ML_ICRITERIA}})<ins style="font-weight: bold; text-decoration: none;">. In both cases</ins>, <ins style="font-weight: bold; text-decoration: none;">if {{TAG|ML_CTIFOR}} is updated</ins>, <ins style="font-weight: bold; text-decoration: none;">it is set to </ins></div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors in the history) *(1.0 + {{TAG|ML_CX}}).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.<del style="font-weight: bold; text-decoration: none;">3 </del>and 0. For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.<ins style="font-weight: bold; text-decoration: none;">2 and 0.0 {{TAG|ML_ICRITERIA}}=1 and, 0.0 </ins>and 0<ins style="font-weight: bold; text-decoration: none;">.3 for {{TAG|ML_ICRITERIA}}=2</ins>. For training runs using heating, the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to {{TAG|ML_CX}}=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}}.</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}} <ins style="font-weight: bold; text-decoration: none;">for {{TAG|ML_ICRITERIA}}=1, and it is currently fixed to 400 for {{TAG|ML_ICRITERIA}}=2</ins>.</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Related tags and articles ==</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>== Related tags and articles ==</div></td></tr> </table>

Kresse https://vasp.at/wiki/index.php?title=ML_CX&diff=16553&oldid=prev 2022-04-08T12:44:17Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 12:44, 8 April 2022</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l20">Line 20:</td> <td colspan="2" class="diff-lineno">Line 20:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>----</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>----</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[[Category:INCAR tag]][[Category:Machine <del style="font-weight: bold; text-decoration: none;">Learning]][[Category:Machine Learned Force Fields</del>]]</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>[[Category:INCAR tag]][[Category:Machine<ins style="font-weight: bold; text-decoration: none;">-learned force fields</ins>]]</div></td></tr> </table>

Karsai https://vasp.at/wiki/index.php?title=ML_CX&diff=15666&oldid=prev 2022-04-07T07:21:50Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 07:21, 7 April 2022</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l1">Line 1:</td> <td colspan="2" class="diff-lineno">Line 1:</td></tr> <tr><td colspan="2" class="diff-side-deleted"></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div><ins style="font-weight: bold; text-decoration: none;">{{DISPLAYTITLE:ML_CX}}</ins></div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAGDEF|ML_CX|[real]|0.0}}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAGDEF|ML_CX|[real]|0.0}}</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l13">Line 13:</td> <td colspan="2" class="diff-lineno">Line 14:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}}.</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}}.</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>== Related <del style="font-weight: bold; text-decoration: none;">Tags </del>and <del style="font-weight: bold; text-decoration: none;">Sections</del>==</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>== Related <ins style="font-weight: bold; text-decoration: none;">tags </ins>and <ins style="font-weight: bold; text-decoration: none;">articles </ins>==</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_LMLFF}}, {{TAG|ML_ICRITERIA}}, {{TAG|ML_CTIFOR}}, {{TAG|ML_MHIS}}, {{TAG|ML_CSIG}}, {{TAG|ML_CSLOPE}}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_LMLFF}}, {{TAG|ML_ICRITERIA}}, {{TAG|ML_CTIFOR}}, {{TAG|ML_MHIS}}, {{TAG|ML_CSIG}}, {{TAG|ML_CSLOPE}}</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l19">Line 19:</td> <td colspan="2" class="diff-lineno">Line 20:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>----</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>----</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>[[Category:INCAR]][[Category:Machine Learning]][[Category:Machine Learned Force Fields<del style="font-weight: bold; text-decoration: none;">]][[Category: Alpha</del>]]</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>[[Category:INCAR <ins style="font-weight: bold; text-decoration: none;">tag</ins>]][[Category:Machine Learning]][[Category:Machine Learned Force Fields]]</div></td></tr> </table>

Karsai https://vasp.at/wiki/index.php?title=ML_CX&diff=13304&oldid=prev 2021-11-23T11:51:47Z

<p></p> <table style="background-color: #fff; color: #202122;" data-mw="interface"> <col class="diff-marker" /> <col class="diff-content" /> <col class="diff-marker" /> <col class="diff-content" /> <tr class="diff-title" lang="en"> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">← Older revision</td> <td colspan="2" style="background-color: #fff; color: #202122; text-align: center;">Revision as of 11:51, 23 November 2021</td> </tr><tr><td colspan="2" class="diff-lineno" id="mw-diff-left-l7">Line 7:</td> <td colspan="2" class="diff-lineno">Line 7:</td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history (see {{TAG|ML_ICRITERIA}}), specifically,</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>If {{TAG|ML_ICRITERIA}}&gt;0, {{TAG|ML_CTIFOR}} is set to the average of the Bayesian errors of the forces stored in history (see {{TAG|ML_ICRITERIA}}), specifically,</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors) *(1.0 + {{TAG|ML_CX}}).</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_CTIFOR}} = (average of the stored Bayesian errors <ins style="font-weight: bold; text-decoration: none;">in the history</ins>) *(1.0 + {{TAG|ML_CX}}).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.3 and 0. For heating <del style="font-weight: bold; text-decoration: none;">run </del>the default usually results in very <del style="font-weight: bold; text-decoration: none;">consistent and </del>well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to ML_CX=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>Obviously setting  {{TAG|ML_CX}} to a positive value will result in fewer first principles calculations and fewer updates of the MLFF, whereas negative values result in more frequent first principles calculations (as well as updates of the MLFF). Typical values of  {{TAG|ML_CX}} are between -0.3 and 0. For <ins style="font-weight: bold; text-decoration: none;">training runs using </ins>heating<ins style="font-weight: bold; text-decoration: none;">, </ins>the default usually results in very well balanced machine learned force fields. When the training is performed at a fixed temperature, it is often desirable to decrease to <ins style="font-weight: bold; text-decoration: none;">{{TAG|</ins>ML_CX<ins style="font-weight: bold; text-decoration: none;">}}</ins>=-0.1, in order to increase the number of first principle calculations and thus the size of the training set (the default can result in too few training data).</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}}.</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>The number of entries in the history are controlled by  {{TAG|ML_MHIS}}.</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> <tr><td class="diff-marker" data-marker="−"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #ffe49c; vertical-align: top; white-space: pre-wrap;"><div>== Related Tags and Sections ==</div></td><td class="diff-marker" data-marker="+"></td><td style="color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #a3d3ff; vertical-align: top; white-space: pre-wrap;"><div>== Related Tags and Sections==</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_LMLFF}}, {{TAG|ML_ICRITERIA}}, {{TAG|ML_CTIFOR}}, {{TAG|ML_MHIS}}, {{TAG|ML_CSIG}}, {{TAG|ML_CSLOPE}}</div></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><div>{{TAG|ML_LMLFF}}, {{TAG|ML_ICRITERIA}}, {{TAG|ML_CTIFOR}}, {{TAG|ML_MHIS}}, {{TAG|ML_CSIG}}, {{TAG|ML_CSLOPE}}</div></td></tr> <tr><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td><td class="diff-marker"></td><td style="background-color: #f8f9fa; color: #202122; font-size: 88%; border-style: solid; border-width: 1px 1px 1px 4px; border-radius: 0.33em; border-color: #eaecf0; vertical-align: top; white-space: pre-wrap;"><br></td></tr> </table>

Kresse