An Improved Convolutional Neural Network Algorithm and Its Application in Multilabel Image Labeling

<table class="table-group" id="tab3"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Methods</td><td class="align_center">CNN</td><td class="align_center">DCCNN</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">Time (s)</td><td class="align_center">277.411</td><td class="align_center">41.446</td></tr><tr><td class="align_left">Number of iterations</td><td class="align_center">2500</td><td class="align_center">100</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Comparison of time and number of iterations required to reach a MAP value of 93% using the CNN and DCCNN.</div>

Computational Intelligence and Neuroscience

tab3

Table 3

Table 3: An Improved Convolutional Neural Network Algorithm and Its Application in Multilabel Image Labeling 