BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures

Frontiers in Neuroinformatics

Neuroscience

Jakub Fil¹  Edward George Jones¹  Steve Furber¹  Michael Hopkins² 

[1] Advanced Processor Technologies Group, Department of Computer Science, The University of Manchester, Manchester, United Kingdom;null;

关键词: single-pass learning;    neuromorphic;    efficient inference;    classification;    machine learning;    robust;    event-based;    IoT;   

DOI  :  10.3389/fninf.2023.1125844

 received in 2022-12-16, accepted in 2023-03-03,  发布年份 2023

来源: Frontiers

【 摘 要 】

We present an innovative working mechanism (the SBC memory) and surrounding infrastructure (BitBrain) based upon a novel synthesis of ideas from sparse coding, computational neuroscience and information theory that enables fast and adaptive learning and accurate, robust inference. The mechanism is designed to be implemented efficiently on current and future neuromorphic devices as well as on more conventional CPU and memory architectures. An example implementation on the SpiNNaker neuromorphic platform has been developed and initial results are presented. The SBC memory stores coincidences between features detected in class examples in a training set, and infers the class of a previously unseen test example by identifying the class with which it shares the highest number of feature coincidences. A number of SBC memories may be combined in a BitBrain to increase the diversity of the contributing feature coincidences. The resulting inference mechanism is shown to have excellent classification performance on benchmarks such as MNIST and EMNIST, achieving classification accuracy with single-pass learning approaching that of state-of-the-art deep networks with much larger tuneable parameter spaces and much higher training costs. It can also be made very robust to noise. BitBrain is designed to be very efficient in training and inference on both conventional and neuromorphic architectures. It provides a unique combination of single-pass, single-shot and continuous supervised learning; following a very simple unsupervised phase. Accurate classification inference that is very robust against imperfect inputs has been demonstrated. These contributions make it uniquely well-suited for edge and IoT applications.

【 授权许可】

Unknown   
Copyright © 2023 Hopkins, Fil, Jones and Furber.