Cargando…
BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures
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 d...
Autores principales: | , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10071999/ https://www.ncbi.nlm.nih.gov/pubmed/37025552 http://dx.doi.org/10.3389/fninf.2023.1125844 |
_version_ | 1785019297736687616 |
---|---|
author | Hopkins, Michael Fil, Jakub Jones, Edward George Furber, Steve |
author_facet | Hopkins, Michael Fil, Jakub Jones, Edward George Furber, Steve |
author_sort | Hopkins, Michael |
collection | PubMed |
description | 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. |
format | Online Article Text |
id | pubmed-10071999 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2023 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-100719992023-04-05 BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures Hopkins, Michael Fil, Jakub Jones, Edward George Furber, Steve Front Neuroinform Neuroscience 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. Frontiers Media S.A. 2023-03-21 /pmc/articles/PMC10071999/ /pubmed/37025552 http://dx.doi.org/10.3389/fninf.2023.1125844 Text en Copyright © 2023 Hopkins, Fil, Jones and Furber. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Neuroscience Hopkins, Michael Fil, Jakub Jones, Edward George Furber, Steve BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures |
title | BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures |
title_full | BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures |
title_fullStr | BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures |
title_full_unstemmed | BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures |
title_short | BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures |
title_sort | bitbrain and sparse binary coincidence (sbc) memories: fast, robust learning and inference for neuromorphic architectures |
topic | Neuroscience |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10071999/ https://www.ncbi.nlm.nih.gov/pubmed/37025552 http://dx.doi.org/10.3389/fninf.2023.1125844 |
work_keys_str_mv | AT hopkinsmichael bitbrainandsparsebinarycoincidencesbcmemoriesfastrobustlearningandinferenceforneuromorphicarchitectures AT filjakub bitbrainandsparsebinarycoincidencesbcmemoriesfastrobustlearningandinferenceforneuromorphicarchitectures AT jonesedwardgeorge bitbrainandsparsebinarycoincidencesbcmemoriesfastrobustlearningandinferenceforneuromorphicarchitectures AT furbersteve bitbrainandsparsebinarycoincidencesbcmemoriesfastrobustlearningandinferenceforneuromorphicarchitectures |