On improving deep learning generalization with adaptive sparse connectivity

Abstract

Large neural networks are very successful in various tasks. However, with limited data, the generalization capabilities of deep neural networks are also very limited. In this paper, we empirically start showing that intrinsically sparse neural networks with adaptive sparse connectivity, which by design have a strict parameter budget during the training phase, have better generalization capabilities than their fully-connected counterparts. Besides this, we propose a new technique to train these sparse models by combining the Sparse Evolutionary Training (SET) procedure with neurons pruning. Operated on MultiLayer Perceptron (MLP) and tested on 15 datasets, our proposed technique zeros out around 50% of the hidden neurons during training, while having a linear number of parameters to optimize with respect to the number of neurons. The results show a competitive classification and generalization performance.

ICML 2019 Workshop on Understanding and Improving Generalization in Deep Learning

References in corpus (6)

• On Large-Batch Training for Deep Learning: Generalization Gap and Sharp Minima
• SNIP: Single-shot Network Pruning based on Connection Sensitivity
• Computing Nonvacuous Generalization Bounds for Deep (Stochastic) Neural Networks with Many More Parameters than Training Data
• Exploring Sparsity in Recurrent Neural Networks
• Parameter Efficient Training of Deep Convolutional Neural Networks by Dynamic Sparse Reparameterization
• Low-Memory Neural Network Training: A Technical Report

Cited by in corpus (2)

• Sparse deep neural networks for modeling aluminum electrolysis dynamics
• Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware