MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
复制标题
DOI：
10.1109/cvpr.2018.00171
复制
发表时间：
2017-11
期刊：
影响因子：
--
通讯作者：
A. Gordon;Elad Eban;Ofir Nachum;Bo Chen;Tien-Ju Yang;E. Choi
中科院分区：
文献类型：
--
作者：
A. Gordon;Elad Eban;Ofir Nachum;Bo Chen;Tien-Ju Yang;E. Choi
We present MorphNet, an approach to automate the design of neural network structures. MorphNet iteratively shrinks and expands a network, shrinking via a resource-weighted sparsifying regularizer on activations and expanding via a uniform multiplicative factor on all layers. In contrast to previous approaches, our method is scalable to large networks, adaptable to specific resource constraints (e.g. the number of floating-point operations per inference), and capable of increasing the network's performance. When applied to standard network architectures on a wide variety of datasets, our approach discovers novel structures in each domain, obtaining higher performance while respecting the resource constraint.
