A Federated Learning Protocol for Spiking Neural Membrane Systems

Mihail-Iulian Pleṣa

doi:10.1142/S012906572450062X

A Federated Learning Protocol for Spiking Neural Membrane Systems

2024-08-30

0

PRE

AI

DOI：10.1142/S012906572450062X

Original

Original request for help

Save

Abstract

En 中文

Although deep learning models have shown promising results in solving problems related to image recognition or natural language processing, they do not match how the biological brain works. Some of the differences include the amount of energy consumed, the way neurons communicate, or the way they learn. To close the gap between artificial neural networks and biological ones, researchers proposed the spiking neural network. Layered Spiking Neural P systems (LSN P systems) are networks of spiking neurons used to solve various classification problems. In this paper, we study the LSN P systems in the context of a federated learning client-server architecture over horizontally partitioned data. We analyze the privacy implications of pre-trained LSN P systems through membership inference attacks. We also perform experiments to assess the performance of an LSN P system trained in the federated learning setup. Our findings suggest that LSN P systems demonstrate higher accuracy and faster convergence compared to federated algorithms based on either perceptron or spiking neural networks.

Keywords:

Spiking neural P systems

privacy-preserving

cryptography

layered spiking neural P systems

A Federated Learning Protocol for Spiking Neural Membrane Systems

Abstract

Journal

Organization