MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks

CVPR 2018 Ariel Gordon • Elad Eban • Ofir Nachum • Bo Chen • Hao Wu • Tien-Ju Yang • Edward 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.

Full paper

Evaluation


No evaluation results yet. Help compare this paper to other papers by submitting the tasks and evaluation metrics from the paper.