Algorithmic evaluation demonstrates improved deep network performance under strict compute budgets across diverse datasets, highlighting an efficient automated architecture design approach.
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.
No takes yet. Share an insight, caveat, or question.
Gordon et al. (2018) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: