Benchmarking Predictive Coding Networks -- Made Simple

TL;DR

This paper introduces PCX, a simple and efficient library for benchmarking predictive coding networks (PCNs), enabling large-scale experiments, achieving new state-of-the-art results, and identifying current limitations to guide future research.

Contribution

The authors present PCX, an open-source library that standardizes benchmarks for PCNs, facilitating scalable experiments and advancing the state-of-the-art in the field.

Findings

Achieved state-of-the-art results on multiple datasets.

Enabled testing of larger architectures on complex data.

Identified key limitations and future directions for PCNs.

Abstract

In this work, we tackle the problems of efficiency and scalability for predictive coding networks (PCNs) in machine learning. To do so, we propose a library, called PCX, that focuses on performance and simplicity, and use it to implement a large set of standard benchmarks for the community to use for their experiments. As most works in the field propose their own tasks and architectures, do not compare one against each other, and focus on small-scale tasks, a simple and fast open-source library and a comprehensive set of benchmarks would address all these concerns. Then, we perform extensive tests on such benchmarks using both existing algorithms for PCNs, as well as adaptations of other methods popular in the bio-plausible deep learning community. All this has allowed us to (i) test architectures much larger than commonly used in the literature, on more complex datasets; (ii)~reach new state-of-the-art results in all of the tasks and datasets provided; (iii)~clearly highlight what the current limitations of PCNs are, allowing us to state important future research directions. With the hope of galvanizing community efforts towards one of the main open problems in the field, scalability, we release code, tests, and benchmarks. Link to the library: https://github.com/liukidar/pcx