Deep Rewiring: Training very sparse deep networks

Guillaume Bellec, David Kappel, Wolfgang Maass, Robert Legenstein

Abstract: Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods exist for pruning connections of a neural network after it was trained without connectivity constraints. We present an algorithm, DEEP R, that enables us to train directly a sparsely connected neural network. DEEP R automatically rewires the network during supervised training so that connections are there where they are most needed for the task, while its total number is all the time strictly bounded. We demonstrate that DEEP R can be used to train very sparse feedforward and recurrent neural networks on standard benchmark tasks with just a minor loss in performance. DEEP R is based on a rigorous theoretical foundation that views rewiring as stochastic sampling of network configurations from a posterior.

TL;DR: The paper presents Deep Rewiring, an algorithm that can be used to train deep neural networks when the network connectivity is severely constrained during training.

Keywords: deep learning, pruning, LSTM, convolutional networks, recurrent neural network, sparse networks, neuromorphic hardware, energy efficient computing, low memory hardware, stochastic differential equation, fokker-planck equation

Code: [ 4 community implementations](https://paperswithcode.com/paper/?openreview=BJ_wN01C-)

Community Implementations: [ 6 code implementations](https://www.catalyzex.com/paper/arxiv:1711.05136/code)