Learning in Feedforward Neural Networks Accelerated by Transfer Entropy

TL;DR

This paper introduces a novel training algorithm for feedforward neural networks that leverages transfer entropy to measure and utilize causal feedback connections, aiming to enhance training efficiency.

Contribution

It presents an information-theoretical method using transfer entropy to analyze and incorporate feedback causal relationships into neural network training.

Findings

TE-based feedback improves training performance

Method quantifies causal influence between nodes

Enhanced understanding of information flow in networks

Abstract

Current neural networks architectures are many times harder to train because of the increasing size and complexity of the used datasets. Our objective is to design more efficient training algorithms utilizing causal relationships inferred from neural networks. The transfer entropy (TE) was initially introduced as an information transfer measure used to quantify the statistical coherence between events (time series). Later, it was related to causality, even if they are not the same. There are only few papers reporting applications of causality or TE in neural networks. Our contribution is an information-theoretical method for analyzing information transfer between the nodes of feedforward neural networks. The information transfer is measured by the TE of feedback neural connections. Intuitively, TE measures the relevance of a connection in the network and the feedback amplifies this connection. We introduce a backpropagation type training algorithm that uses TE feedback connections to improve its performance.