BindsNET: A machine learning-oriented spiking neural networks library in Python

TL;DR

BindsNET is a Python library that simplifies the development and simulation of spiking neural networks for machine learning and reinforcement learning, leveraging PyTorch for fast computation and providing easy integration with OpenAI gym.

Contribution

It introduces a user-friendly, flexible Python framework for rapid prototyping of spiking neural networks tailored to machine learning applications, with GPU support and reinforcement learning integration.

Findings

Enables fast CPU and GPU simulation of large spiking networks.

Provides an interface for reinforcement learning tasks via OpenAI gym.

Facilitates large-scale machine learning experimentation with spiking neural networks.

Abstract

The development of spiking neural network simulation software is a critical component enabling the modeling of neural systems and the development of biologically inspired algorithms. Existing software frameworks support a wide range of neural functionality, software abstraction levels, and hardware devices, yet are typically not suitable for rapid prototyping or application to problems in the domain of machine learning. In this paper, we describe a new Python package for the simulation of spiking neural networks, specifically geared towards machine learning and reinforcement learning. Our software, called BindsNET, enables rapid building and simulation of spiking networks and features user-friendly, concise syntax. BindsNET is built on top of the PyTorch deep neural networks library, enabling fast CPU and GPU computation for large spiking networks. The BindsNET framework can be adjusted to meet the needs of other existing computing and hardware environments, e.g., TensorFlow. We also provide an interface into the OpenAI gym library, allowing for training and evaluation of spiking networks on reinforcement learning problems. We argue that this package facilitates the use of spiking networks for large-scale machine learning experimentation, and show some simple examples of how we envision BindsNET can be used in practice. BindsNET code is available at https://github.com/Hananel-Hazan/bindsnet