Welcome to Rockpool
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.
Rockpool is an open-source project managed by SynSense.
The basics
In depth
- 🛠 Low-level
ModuleAPI - ⏱ High-level
TimedModuleAPI - [𝝺] Low-level functional API
- 🏃🏽♀️ Training a Rockpool network with Jax
- 👩🏽🔬 Advanced Jax training topics
- 🔥 Building Rockpool modules with Torch
- 👩🏼🚒 Training a Rockpool network with Torch
- How To: Configure and perform constrained optimization in Rockpool
Tutorials
- ∇ Gradient descent training of a rate-based recurrent network
- ⚡️ Training a spiking network with Jax
- ⚡️ Training a spiking network with Torch
- 🐰 Easter with Rockpool 🥚
- 👹 Adversarial training
- 🔊 Training an audio classification task using Torch 🔥
- WaveSense: Training a Spiking Neural Network with Temporal Convolutions
Xylo™ inference processors
Xylo™ IMU
DYNAP-SE2 mixed-signal processor
Advanced topics
Developer documentation