BindsNET: A Machine Learning-Oriented Spiking Neural Networks Library in Python

• Published in: Frontiers in neuroinformatics Vol. 12; p. 89
• Main Authors: Hazan, Hananel, Saunders, Daniel J., Khan, Hassaan, Patel, Devdhar, Sanghavi, Darpan T., Siegelmann, Hava T., Kozma, Robert
• Format: Journal Article
• Language: English
• Published: Switzerland Frontiers Research Foundation 12.12.2018; Frontiers Media S.A
• Subjects: Algorithms; Artificial intelligence; Back propagation; Computer applications; Computer programs; Datasets; Deep learning; Firing pattern; GPU-computing; Learning algorithms; Libraries; Machine learning; Neural networks; Neuroinformatics; Neurons; Neurosciences; Ordinary differential equations; python (programming language); PyTorch; Realism; Reinforcement; reinforcement learning (RL); Software; Software packages; spiking Network; Teaching methods; Trends; GPU-computing; PyTorch; spiking Network; machine learning; python (programming language); reinforcement learning (RL)
• ISSN: 1662-5196; 1662-5196
• DOI: 10.3389/fninf.2018.00089

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 toward 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 the PyTorch deep neural networks library, facilitating the implementation of spiking neural networks on fast CPU and GPU computational platforms. Moreover, the BindsNET framework can be adjusted to utilize other existing computing and hardware backends; e.g., TensorFlow and SpiNNaker. We provide an interface with the OpenAI gym library, allowing for training and evaluation of spiking networks on reinforcement learning environments. We argue that this package facilitates the use of spiking networks for large-scale machine learning problems and show some simple examples by using BindsNET in practice.