SENeCA by Imec

RISC-V based digital neuromorphic processor

SENeCA At A Glance

Release Year: 2022
Status: Released
Chip Type: Digital
Software: SENeCA SDK
Applications: Extreme edge applications
On-Chip Learning: true

SENeCA is a RISC-V-based digital neuromorphic processor targeting extreme edge applications by accelerating Spiking Neural Networks inside or near sensors and small devices where ultra-low power and adaptivity are required. It inherits fundamental properties from the biological brain: spatio-temporal sparsity exploitation, parallel processing, infinite scalability, low-precision parameters, asynchronous non-deterministic execution, adaptation and fault-tolerance architecture, interconnect of neuron cluster cores with RISC-V-based instruction set.

Overview

SENeCA is a RISC-V-based digital neuromorphic processor targeting extreme edge applications by accelerating Spiking Neural Networks inside or near sensors and small devices where ultra-low power and adaptivity are required. It inherits fundamental properties from the biological brain: spatio-temporal sparsity exploitation, parallel processing, infinite scalability, low-precision parameters, asynchronous non-deterministic execution, adaptation and fault-tolerance architecture, interconnect of neuron cluster cores with RISC-V-based instruction set. SENeCA has fully programmable neuron models and learning/adaptivity algorithms. It is accessible for academic research.

Help Us Improve this Guide

Our hardware guide is community-maintained. If you know of a chip we should add, see an error, or have updated information, please let us know by opening an issue on our GitHub repository.

Announcing Open Neuromorphic Research: Community Peer Review for Open Science

Announcing Open Neuromorphic Research: Community Peer Review for Open Science

Submit your open-source neuromorphic projects for transparent community review and recognition through the ONR Program.

Diverse and United: Neuromorphic Open Source Leaders Form ONM Collaboration Network

Diverse and United: Neuromorphic Open Source Leaders Form ONM Collaboration Network

Following a landmark panel, leading projects like BindsNET, Brian, GeNN, and snnTorch unite to form the inaugural Open Neuromorphic Collaboration Network, putting our strategic vision into action.

Efficient Compression for Event-Based Data in Neuromorphic Applications

Efficient Compression for Event-Based Data in Neuromorphic Applications

Discover methods to efficiently encode and store event-based data from high-resolution event cameras, striking a balance between file size and fast retrieval for spiking neural network training.