A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDP7177/_pdf">the original URL</a>. The file type is <code>application/pdf</code>.
<i title="Institute of Electronics, Information and Communications Engineers (IEICE)">
<a target="_blank" rel="noopener" href="https://fatcat.wiki/container/xosmgvetnbf4zpplikelekmdqe" style="color: black;">IEICE transactions on information and systems</a>
This paper presents a method for reducing the redundancy in both fully connected layers and convolutional layers of trained neural network models. The proposed method consists of two steps, 1) Neuro-Coding: to encode the behavior of each neuron by a vector composed of its outputs corresponding to actual inputs and 2) Neuro-Unification: to unify the neurons having the similar behavioral vectors. Instead of just pruning one of the similar neurons, the proposed method let the remaining neuron<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1587/transinf.2019edp7177">doi:10.1587/transinf.2019edp7177</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uawh24gzobhenhspsezyrg3qxm">fatcat:uawh24gzobhenhspsezyrg3qxm</a> </span>
more »... te the behavior of the pruned one. Therefore, the proposed method can reduce the number of neurons with small sacrifice of accuracy without retraining. Our method can be applied for compressing convolutional layers as well. In the convolutional layers, the behavior of each channel is encoded by its output feature maps, and channels whose behaviors can be well emulated by other channels are pruned and update the remaining weights. Through several experiments, we comfirmed that the proposed method performs better than the existing methods.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201107035624/https://www.jstage.jst.go.jp/article/transinf/E103.D/5/E103.D_2019EDP7177/_pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/59/30/5930b9ea50da571cfa35b139a7be73d1d4131f16.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1587/transinf.2019edp7177"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>