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

Published in

(2018)

External Links:

Generate Graph DownloadPDF

TL;DR

It is argued that this package facilitates the use of spiking networks for large-scale machine learning problems and some simple examples by using BindsNET in practice are shown.

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 toward machine learning and reinforcement learning. Our software, called BindsNET1, 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.

Authors

H. Siegelmann

2 papers

Hananel Hazan

1 papers

D. J. Saunders

1 papers

References63 items

Brian2GeNN: a system for accelerating a large variety of spiking neural networks with graphics hardware

Unsupervised Learning with Self-Organizing Spiking Neural Networks

Conversion of analog to spiking neural networks using sparse temporal coding

Prefrontal cortex as a meta-reinforcement learning system

Unsupervised Feature Learning With Winner-Takes-All Based STDP

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

Published in

(2018)

External Links:

Generate Graph DownloadPDF

TL;DR

It is argued that this package facilitates the use of spiking networks for large-scale machine learning problems and some simple examples by using BindsNET in practice are shown.

Abstract

Authors

H. Siegelmann

2 papers

Hananel Hazan

1 papers

D. J. Saunders

1 papers

References63 items

Brian2GeNN: a system for accelerating a large variety of spiking neural networks with graphics hardware

Unsupervised Learning with Self-Organizing Spiking Neural Networks

Conversion of analog to spiking neural networks using sparse temporal coding

Prefrontal cortex as a meta-reinforcement learning system

Unsupervised Feature Learning With Winner-Takes-All Based STDP

Hassaan Khan

1 papers

Devdhar Patel

1 papers

Darpan T. Sanghavi

1 papers

TL;DR

Abstract

Authors

References63 items

Brian2GeNN: a system for accelerating a large variety of spiking neural networks with graphics hardware

Unsupervised Learning with Self-Organizing Spiking Neural Networks

Conversion of analog to spiking neural networks using sparse temporal coding

Prefrontal cortex as a meta-reinforcement learning system

Unsupervised Feature Learning With Winner-Takes-All Based STDP

TL;DR

Abstract

Authors

References63 items

Brian2GeNN: a system for accelerating a large variety of spiking neural networks with graphics hardware

Unsupervised Learning with Self-Organizing Spiking Neural Networks

Conversion of analog to spiking neural networks using sparse temporal coding

Prefrontal cortex as a meta-reinforcement learning system

Unsupervised Feature Learning With Winner-Takes-All Based STDP

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning

Conversion of Continuous-Valued Deep Networks to Efficient Event-Driven Networks for Image Classification

Automatic differentiation in PyTorch

Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms

Software for Brain Network Simulations: A Comparative Study

Gradient Descent for Spiking Neural Networks

Spatio-Temporal Backpropagation for Training High-Performance Spiking Neural Networks

First-Spike-Based Visual Categorization Using Reward-Modulated STDP

STDP-based spiking deep neural networks for object recognition

Training Deep Spiking Neural Networks Using Backpropagation

Supervised Learning Based on Temporal Coding in Spiking Neural Networks

Toward an Integration of Deep Learning and Neuroscience

OpenAI Gym

Theano: A Python framework for fast computation of mathematical expressions

Deep Spiking Networks

GeNN: a code generation framework for accelerated brain simulations

MXNet: A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems

Spiking Deep Networks with LIF Neurons

TrueNorth: Design and Tool Flow of a 65 mW 1 Million Neuron Programmable Neurosynaptic Chip

Unsupervised learning of digit recognition using spike-timing-dependent plasticity

ANNarchy: a code generation approach to neural simulations on parallel hardware

Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing

CARLsim 3: A user-friendly and highly optimized library for the creation of neurobiologically detailed spiking neural networks

Towards Biologically Plausible Deep Learning

cuDNN: Efficient Primitives for Deep Learning

Caffe: Convolutional Architecture for Fast Feature Embedding

NeuCube: A spiking neural network architecture for mapping, learning and understanding of spatio-temporal brain data

Nengo: a Python tool for building large-scale functional brain models

Spectral Networks and Locally Connected Networks on Graphs

Spiking neural network connectivity and its potential for temporal sensory processing and variable binding

Equation-oriented specification of neural models for simulations

Python as a Federation Tool for GENESIS 3.0

SpiNNaker: Design and Implementation of a GALS Multicore System-on-Chip

Scikit-learn: Machine Learning in Python

NeMo: A Platform for Neural Modelling of Spiking Neurons Using GPUs

PyNN: A Common Interface for Neuronal Network Simulators

NEURON and Python

Reinforcement Learning Through Modulation of Spike-Timing-Dependent Synaptic Plasticity

NEST (NEural Simulation Tool)

The NEURON Book: Index

Simple model of spiking neurons

Automatic Detection and Segmentation of Evolving Processes in 3D Medical Images: Application to Multiple Sclerosis

Rank order coding

Networks of spiking neurons: the third generation of neural network models

Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPs

Chainer : a Next-Generation Open Source Framework for Deep Learning

Deep Learning

TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. URL https://www.tensorflow.org/. Software available from tensorflow.org

Brian simulator

A Technical Overview of the Neural Engineering Framework

Learning Multiple Layers of Features from Tiny Images

Spiking Neuron Models

SPIKING NEURON MODELS Single Neurons , Populations , Plasticity

Lower Bounds for the Computational Power of Networks of Spiking Neurons

Networks of Spiking Neurons: The Third Generation of Neural Network Models

References References

Is backpropagation biologically plausible?

The Organization of Behavior: A Neuropsychological Theory

Field of Study

Journal Information

Name

Volume