Neural Architecture Construction using EnvelopeNets

By Purushotham Kamath, Abhishek Singh, Debo Dutta. 2018

14 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware (2018, neutral): “2 RELATED WORK The use of machine learning techniques, such as reinforcement learning or neuro-evolution, to replace human experts in designing neural network architectures, usually referred to as neural architecture search, has drawn an increasing interest (Zoph & Le, 2017; Liu et al., 2018a;b;c; C”
DATA: Differentiable ArchiTecture Approximation (2019, unknown): “, evolution-based NAS [13, 18, 26, 41, 43, 44, 45, 47], reinforcement learning-based NAS [2, 3, 21, 42, 56, 59, 60], and gradient-based NAS [11, 34, 35, 46, 53], which has achieved significant successes in a multitude of fields, including image classification [4, 12, 21, 30, 31, 34, 44, 53, 60], sem”
Differentiable Architecture Search with Ensemble Gumbel-Softmax (2019, methodology): “Evolution-based neural architecture search meth-ods (Real et al., 2017; Miikkulainen et al., 2017; Real et al., 2018; Elsken et al., 2018b; Kamath et al., 2018) utilize evolution algorithms to generate neural architecture, automatically.”
DATA: Differentiable ArchiTecture Approximation With Distribution Guided Sampling (2020, methodology): “Recently, [11], [13], [14], [15], [16] bring this idea back by applying evolutionary algorithms in a CNN search space.”
Fast Neural Architecture Construction using EnvelopeNets (2018, background): “It can be shown (19) that for a simple single stage network, with some assumptions, the relative MSE of a pruned network relative to its generating EnvelopeNet is minimized by pruning the filter with the lowest sum of the squared `2-norm of a filter featuremap.”