Year: 2018
Type: article
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 \texttt{BindsNET}, enables rapid building and simulation of spiking networks and features user-friendly, concise syntax. \texttt{BindsNET} is built on the \texttt{PyTorch} deep neural networks library, facilitating the implementation of spiking neural networks on fast CPU and GPU computational platforms. Moreover, the \texttt{BindsNET} framework can be adjusted to utilize other existing computing and hardware backends; e.g., \texttt{TensorFlow} and \texttt{SpiNNaker}. We provide an interface with the OpenAI \texttt{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 \texttt{BindsNET} in practice. \blfootnote{\texttt{BindsNET} code is available at \texttt{https://github.com/Hananel-Hazan/bindsnet}. To install the version of the code used for this paper, use \texttt{pip install bindsnet=0.2.1}.}
Source: Frontiers in Neuroinformatics
Authors: Hananel Hazan, Daniel J. Saunders, Hassaan Khan, Devdhar Patel, Darpan T. Sanghavi, Hava T. Siegelmann, Robert Kozma
Institution: University of Massachusetts Amherst
Language: English
Subfield: Electrical and Electronic Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $3,801
OpenAlex ID: W2807457908
