Learning in Feedforward Neural Networks Accelerated by Transfer Entropy
This work addresses the problem of inefficient training for researchers and practitioners in machine learning, but it appears incremental as it builds on existing backpropagation methods with a novel feedback mechanism.
The authors tackled the challenge of training increasingly large and complex neural networks by developing a training algorithm that uses transfer entropy to measure and amplify causal relationships between nodes, resulting in improved performance.
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.