Research and Verification of Convolutional Neural Network Lightweight in BCI

<table class="table-group" id="tab4"><tr><td><table class="table"><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr class="thead"><td class="align_left" rowspan="2">Structure</td><td class="align_center" rowspan="2">Parameter quantity (M)</td><td class="align_center" colspan="2">Accuracy</td></tr><tr class="thead"><td class="align_center">Batch normalization</td><td class="align_center">No-batch normalization</td></tr><tr><td class="thead-hr" colspan="4"><hr/></td></tr><tr><td class="align_left">SqueezeNet</td><td class="align_center">4.81</td><td class="align_center">N/A</td><td class="align_center">0.7125 ± 0.0004</td></tr><tr><td class="align_left">NVM</td><td class="align_center">3.27</td><td class="align_center">0.7082 ± 0.0002</td><td class="align_center">0.7016 ± 0.0013</td></tr><tr class="table-tr"><td colspan="4"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Improved network quality nuclear accuracy comparison.</div>

Computational and Mathematical Methods in Medicine

tab4

Table 4

Table 4: Research and Verification of Convolutional Neural Network Lightweight in BCI 