Deep Learning Methods for Underwater Target Feature Extraction and Recognition

<table class="fixed-width table-group" id="tab2"><tr><td><table class="table"><colgroup><col style="width:19.17em"/><col style="width:6.56em"/></colgroup><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr class="thead"><td class="align_left">Parameters</td><td class="align_center">Scope</td></tr><tr><td class="thead-hr" colspan="2"><hr/></td></tr><tr><td class="align_left">Activated functions</td><td class="align_center">ReLu</td></tr><tr><td class="align_left">Size of learning rate</td><td class="align_center">0.02~0.05</td></tr><tr><td class="align_left">Decay rate of learning rate</td><td class="align_center">0.0005/Batch</td></tr><tr><td class="align_left">Number of batch processing samples (Batch)</td><td class="align_center">200</td></tr><tr><td class="align_left">Impulse magnitude</td><td class="align_center">0.9</td></tr><tr class="table-tr"><td colspan="2"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

<div>Value choice and selection of typical parameters.</div>

Computational Intelligence and Neuroscience

tab2

Table 2

Table 2: Deep Learning Methods for Underwater Target Feature Extraction and Recognition 