2016年10月05日 17:09:46
阅读数:7445
<span class="tags-box artic-tag-box">
<span class="label">标签:</span>
<a data-track-click="{"mod":"popu_626","con":"momentum"}" class="tag-link" href="http://so.csdn.net/so/search/s.do?q=momentum&t=blog" target="_blank">momentum </a>
<span class="article_info_click">更多</span></span>
<div class="tags-box space">
<span class="label">个人分类:</span>
<a class="tag-link" href="https://blog.csdn.net/u012938704/article/category/6436970" target="_blank">机器学习 </a>
</div>
</div>
<div class="operating">
</div>
</div>
</div>
</div>
<article>
<div id="article_content" class="article_content clearfix csdn-tracking-statistics" data-pid="blog" data-mod="popu_307" data-dsm="post">
<div class="markdown_views">
<p>一、weight decay(权值衰减)使用的目的是防止过拟合。在损失函数中,weight decay是放在正则项(regularization)前面的一个系数,正则项一般指示模型的复杂度,所以weight decay的作用是调节模型复杂度对损失函数的影响,若weight decay很大,则复杂的模型损失函数的值也就大。</p>