On the relationship between predictive coding and backpropagation

Abstract

Artificial neural networks are often interpreted as abstract models of biological neuronal networks, but they are typically trained using the biologically unrealistic backpropagation algorithm and its variants. Predictive coding has been proposed as a potentially more biologically realistic alternative to backpropagation for training neural networks. This manuscript reviews and extends recent work on the mathematical relationship between predictive coding and backpropagation for training feedforward artificial neural networks on supervised learning tasks. Implications of these results for the interpretation of predictive coding and deep neural networks as models of biological learning are discussed along with a repository of functions, Torch2PC, for performing predictive coding with PyTorch neural network models.

References in corpus (7)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Predictive Coding: a Theoretical and Experimental Review
• Two Routes to Scalable Credit Assignment without Weight Symmetry
• Predictive Coding Can Do Exact Backpropagation on Convolutional and Recurrent Neural Networks
• Cortical credit assignment by Hebbian, neuromodulatory and inhibitory plasticity
• Credit Assignment Through Broadcasting a Global Error Vector

Cited by in corpus (3)

• Predictive Coding Networks and Inference Learning: Tutorial and Survey
• Meta predictive learning model of languages in neural circuits
• Bio-Inspired Artificial Neural Networks based on Predictive Coding