MorphNet: Fast & Simple Resource-Constrained Structure Learning of Deep Networks
2018pp. 1586–1595
Citations Over TimeTop 1% of 2018 papers
Abstract
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.
Related Papers
- → Uniform parallel machine scheduling with resource consumption constraint(2014)58 cited
- → Risk-Adjusted Resource Allocation(2013)11 cited
- → A Single-Machine Scheduling Problem with the Controllable Processing Times and the Late Work Criterion(2022)1 cited
- → A Formalization for Distributed Cooperative Sensor Resource Allocation(2008)6 cited
- → Project scheduling under resource constraints: Application of the cumulative global constraint(2009)3 cited