Own a piece of the neuromorphic revolution
The Nengo Brain Board implements a learning, spiking neural network that you can directly program from within Nengo.
These inexpensive boards open neuromorphics up to anyone. Explore and exploit the advantages of neuromorphic computing in the classroom, the innovation lab, or your basement.
Use Nengo’s friendly graphical interface to run parts of your standard Nengo model on power-efficient and fast neuromorphic hardware. These self-contained boards outperform most laptops in terms of both speed and efficiency.
Start by running one of the many demos that come with the board out of the box: visual classifiers, adaptive controllers, reinforcement learning, and more!
Brain Board Features
Use with any Nengo model
Documentation is freely available and frequently updated. Take a look to see how easy it is to get up and running.
Join a growing community of people building Nengo models together.
We offer complete hardware and software integration with a bring-your-own-board model.
Large-scale Nengo Brain Boards
Our small Nengo Brain Boards are just the beginning, developed to be inexpensive and targeting DE1-SoC and PYNQ-Z1 FPGA boards. These initial proof-of-concept Brain Boards offer encouraging results and motivate us to actively continue development! Take a look at this conference paper for more information about the design and performance of our early PYNQ implementation of Nengo Brain Board. See also, the paper presentation and talk for further explanations.
To make neuromorphics easy and fast to deploy at scale, beyond our currently available Nengo Brain Boards, we’re developing larger and more capable versions with researchers at the University of Waterloo, which target larger off-the-shelf Intel and Xilinx FPGAs. This will provide a quick route to get the benefits of neuromorphic computing sooner rather than later. Given the large scale and increasing complexity, we’re working with collaborators to develop special communication protocols to move spiking data efficiently on chip. This project is still in the early stages, but has already generated promising results, showing significantly better performance for high bandwidth and compute intensive use cases.