Integration of Contrastive Predictive Coding and Spiking Neural Networks

TL;DR

This paper explores combining Contrastive Predictive Coding with Spiking Neural Networks to create more biologically plausible predictive models, demonstrating effective classification on MNIST and providing open-source code.

Contribution

It introduces a novel integration of CPC with SNNs, enhancing biological plausibility and showing SNNs can serve as both classifiers and encoders.

Findings

Successful classification of MNIST data

Effective combination of CPC with SNNs

Open-source implementation available

Abstract

This study examines the integration of Contrastive Predictive Coding (CPC) with Spiking Neural Networks (SNN). While CPC learns the predictive structure of data to generate meaningful representations, SNN mimics the computational processes of biological neural systems over time. In this study, the goal is to develop a predictive coding model with greater biological plausibility by processing inputs and outputs in a spike-based system. The proposed model was tested on the MNIST dataset and achieved a high classification rate in distinguishing positive sequential samples from non-sequential negative samples. The study demonstrates that CPC can be effectively combined with SNN, showing that an SNN trained for classification tasks can also function as an encoding mechanism. Project codes and detailed results can be accessed on our GitHub page: https://github.com/vnd-ogrenme/ongorusel-kodlama/tree/main/CPC_SNN