Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Videos

PyGeNN: A Python Library for GPU-Enhanced Neural Networks.

James C Knight¹, Anton Komissarov^2,3, Thomas Nowotny¹

¹Centre for Computational Neuroscience and Robotics, School of Engineering and Informatics, University of Sussex, Brighton, United Kingdom.

Frontiers in Neuroinformatics

|May 10, 2021

Summary

This summary is machine-generated.

Related Concept Videos

Neural Circuits

Neural Circuits

Neural circuits and neuronal pools are two of the main structures found in the nervous system. Neural circuits are networks of neurons that work together to carry out a specific task or process. They consist of interconnected neurons and glial cells, which provide structural and metabolic support.
Neuronal pools are collections of nerve cells with similar functions and interact through chemical and electrical signals. These pools include both interneurons (the central neural circuit nodes that...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Wavelet-based visual compass.

PloS one·2026

Same author

Introduction to the Proceedings of the CNS*2025 Meeting.

Journal of computational neuroscience·2026

Same author

<i>In Vivo</i> Evaluation of a Self-Excitatory Near-Infrared ImmunoSCIFI Probe.

Bioconjugate chemistry·2026

Same author

Efficient event-based delay learning in spiking neural networks.

Nature communications·2025

Same author

Building on models-a perspective for computational neuroscience.

Cerebral cortex (New York, N.Y. : 1991)·2025

Same author

Understanding the mechanism of facilitation in hoverfly TSDNs.

PLoS computational biology·2025

Same journal

Predicting vasovagal syncope during head-up tilt test: three machine learning approaches.

Frontiers in neuroinformatics·2026

Same journal

Decoding basal ganglia motor circuit dysfunction from handwriting: a physics-informed neural signal interpretation framework for Parkinson's disease screening.

Frontiers in neuroinformatics·2026

Same journal

FUSION-AD: interpretable AI framework for risk assessment and subgroup discovery in Alzheimer's disease.

Frontiers in neuroinformatics·2026

Same journal

A 3D-printed phantom to validate subject orientation in 3D imaging and recordings.

Frontiers in neuroinformatics·2026

Same journal

IntegriLAB: a blockchain-enabled electronic lab notebook for reproducible neuroimaging research.

Frontiers in neuroinformatics·2026

Same journal

Long-range correlations in alpha-band of electroencephalogram: a nonlinear embedding and detrended fluctuation analysis.

Frontiers in neuroinformatics·2026

See all related articles

PyGeNN offers a user-friendly Python interface for the GeNN library, enabling efficient GPU-accelerated spiking neural network simulations. This new system significantly speeds up complex neural modeling, even surpassing real-time capabilities for certain simulations.

Area of Science:

Computational Neuroscience
Machine Learning
High-Performance Computing

Background:

Graphics Processing Units (GPUs) are increasingly vital in supercomputing and edge devices.
GeNN is a C++ library for efficient GPU-based spiking neural network (SNN) simulations.
Previous GeNN usage required C++ expertise, limiting accessibility.

Purpose of the Study:

Introduce PyGeNN, a Python package providing full GeNN functionality with minimal overhead.
Enable broader use of GeNN within Python's extensive machine learning and neuroscience ecosystems.
Improve the efficiency and speed of SNN simulations on GPUs.

Main Methods:

Developed PyGeNN, a Python package interfacing with the GeNN C++ library.
Implemented a novel spike recording system to minimize simulation overheads.

Keywords:

GPU benchmarking computational neuroscience high-performance computing parallel computing python spiking neural networks

Related Experiment Videos

Benchmarked PyGeNN and C++ GeNN simulations on modern GPUs, including large-scale models.

Main Results:

PyGeNN offers a more accessible and user-friendly alternative to C++ for GeNN.
The new spike recording system reduces data recording overheads by up to 10x.
PyGeNN enabled simulation of a cortical column model faster than real-time.
Long simulations with complex stimuli and custom learning rules achieved speeds nearly two orders of magnitude faster than real-time.

Conclusions:

PyGeNN significantly enhances the usability and accessibility of GPU-accelerated SNN simulations.
Optimized spike recording and PyGeNN facilitate unprecedented simulation speeds for complex neural models.
PyGeNN empowers researchers to leverage powerful GPU acceleration within the Python ecosystem for advanced neuroscience and machine learning research.