美文网首页
Learning Structured Sparsity in

Learning Structured Sparsity in

作者: 信步闲庭v | 来源:发表于2017-10-28 19:41 被阅读33次

Approach


The optimization target of learning the filter-wise and channel-wise structured sparsity can be defined as:

Our approach tends to remove less important filters and channels. Note that zeroing out a filter in the l-th layer results in a dummy zero output feature map, which in turn makes a corresponding channel in the (l + 1)-th layer useless. Hence, we combine the filter-wise and channel-wise structured sparsity in the learning simultaneously.

Experiment

References:
Learning Structured Sparsity in Deep Neural Networks, Wei Wen, 2016, NIPS

相关文章

网友评论

      本文标题:Learning Structured Sparsity in

      本文链接:https://www.haomeiwen.com/subject/kwpspxtx.html