Target Propagation via Regularized Inversion

TL;DR

This paper introduces a simple, regularized inversion-based target propagation method that offers an alternative to back-propagation, especially effective for training recurrent neural networks on sequence modeling tasks.

Contribution

It presents a novel, easily implementable target propagation algorithm based on regularized inversion, with analysis of its computational complexity and practical advantages.

Findings

Regularized TP improves training of recurrent neural networks.

TP can be more computationally attractive than BP in certain regimes.

Regularization is crucial for the practical success of TP.

Abstract

Target Propagation (TP) algorithms compute targets instead of gradients along neural networks and propagate them backward in a way that is similar yet different than gradient back-propagation (BP). The idea was first presented as a perturbative alternative to back-propagation that may achieve greater accuracy in gradient evaluation when training multi-layer neural networks (LeCun et al., 1989). However, TP has remained more of a template algorithm with many variations than a well-identified algorithm. Revisiting insights of LeCun et al., (1989) and more recently of Lee et al. (2015), we present a simple version of target propagation based on regularized inversion of network layers, easily implementable in a differentiable programming framework. We compare its computational complexity to the one of BP and delineate the regimes in which TP can be attractive compared to BP. We show how our TP can be used to train recurrent neural networks with long sequences on various sequence modeling problems. The experimental results underscore the importance of regularization in TP in practice.