There is a newer version of the record available.

Published March 22, 2023 | Version 2.6
Software documentation Open

Rockpool Documentation

Authors/Creators

  • 1. SynSense

Contributors

  • 1. SynSense
  • 2. SynSnese

Description

Rockpool is a Python package for working with dynamical neural network architectures, particularly for designing event-driven networks for Neuromorphic computing hardware. Rockpool provides a convenient interface for designing, training and evaluating recurrent networks, which can operate both with continuous-time dynamics and event-driven dynamics.

Files

rockpool.pdf

Files (69.4 MB)

Name Size Download all
md5:37bcd08da0943396a9b1c993349106c8
69.4 MB Preview Download

Additional details

Funding

European Commission
ANDANTE - Ai for New Devices And Technologies at the Edge 876925
European Commission
SYNCH - A SYnaptically connected brain-silicon Neural Closed-loop Hybrid system 824162
European Commission
EdgeAI - Edge AI Technologies for Optimised Performance Embedded Processing 101097300
European Commission
TEMPO - Technology and hardware for neuromorphic computing 826655