BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures
Posted on 2022-12-09 - 15:30 authored by Jakub Fil
We present an innovative working mechanism (SBC memory) and surrounding infrastructure (BitBrain) based upon a novel synthesis of ideas from sparse coding, computational neuroscience and information theory that support single-pass and single-shot learning, accurate and robust inference, and the potential for continuous adaptive learning. They are designed to be implemented efficiently on current and future neuromorphic devices as well as on more conventional CPU and memory architectures.
This collection was created as a supplement for a pending publication in "Frontiers in Neuroinformatics: Physical Neuromorphic Computing and its Industrial Applications" and contains an implementation of the BitBrain algorithm in C.
CITE THIS COLLECTION
Fil, Jakub; Furber, Steve; Hopkins, Michael; Jones, Edward (2022). BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures. University of Manchester. Collection. https://doi.org/10.48420/c.6331565.v1
or
Select your citation style and then place your mouse over the citation text to select it.