English

Learning on Arbitrary Graph Topologies via Predictive Coding

Machine Learning 2022-10-13 v3

Abstract

Training with backpropagation (BP) in standard deep learning consists of two main steps: a forward pass that maps a data point to its prediction, and a backward pass that propagates the error of this prediction back through the network. This process is highly effective when the goal is to minimize a specific objective function. However, it does not allow training on networks with cyclic or backward connections. This is an obstacle to reaching brain-like capabilities, as the highly complex heterarchical structure of the neural connections in the neocortex are potentially fundamental for its effectiveness. In this paper, we show how predictive coding (PC), a theory of information processing in the cortex, can be used to perform inference and learning on arbitrary graph topologies. We experimentally show how this formulation, called PC graphs, can be used to flexibly perform different tasks with the same network by simply stimulating specific neurons, and investigate how the topology of the graph influences the final performance. We conclude by comparing against simple baselines trained~with~BP.

Keywords

Cite

@article{arxiv.2201.13180,
  title  = {Learning on Arbitrary Graph Topologies via Predictive Coding},
  author = {Tommaso Salvatori and Luca Pinchetti and Beren Millidge and Yuhang Song and Tianyi Bao and Rafal Bogacz and Thomas Lukasiewicz},
  journal= {arXiv preprint arXiv:2201.13180},
  year   = {2022}
}

Comments

15 pages, 11 figures