{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T16:06:11Z","timestamp":1753891571146,"version":"3.41.2"},"reference-count":57,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,3,21]],"date-time":"2023-03-21T00:00:00Z","timestamp":1679356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neuroinform."],"abstract":"<jats:p>We present an innovative working mechanism (the<jats:italic>SBC memory<\/jats:italic>) and surrounding infrastructure (<jats:italic>BitBrain<\/jats:italic>) 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<jats:italic>BitBrain<\/jats:italic>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.<jats:italic>BitBrain<\/jats:italic>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.<\/jats:p>","DOI":"10.3389\/fninf.2023.1125844","type":"journal-article","created":{"date-parts":[[2023,3,21]],"date-time":"2023-03-21T13:45:38Z","timestamp":1679406338000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["BitBrain and Sparse Binary Coincidence (SBC) memories: Fast, robust learning and inference for neuromorphic architectures"],"prefix":"10.3389","volume":"17","author":[{"given":"Michael","family":"Hopkins","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jakub","family":"Fil","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Edward George","family":"Jones","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Steve","family":"Furber","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2023,3,21]]},"reference":[{"journal-title":"Are Biologically-Inspired Filters Robust Against Image Distortion and Noise?","year":"2022","author":"Adithya","key":"B1"},{"journal-title":"How Do Neurons Operate on Sparse Distributed Representations? A Mathematical Theory of Sparsity, Neurons and Active Dendrites","year":"2016","author":"Ahmad","key":"B2"},{"key":"B3","doi-asserted-by":"publisher","first-page":"1537","DOI":"10.1109\/TCAD.2015.2474396","article-title":"Truenorth: design and tool flow of a 65 mw 1 million neuron programmable neurosynaptic chip","volume":"34","author":"Akopyan","year":"2015","journal-title":"IEEE Trans. Computer Aided Design Integr. Circ. Syst."},{"key":"B4","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1162\/neco.1993.5.1.45","article-title":"Convergent algorithm for sensory receptive field development","volume":"5","author":"Atick","year":"1993","journal-title":"Neural Comput."},{"key":"B5","doi-asserted-by":"crossref","DOI":"10.1142\/3584","author":"Austin","year":"1998","journal-title":"RAM-Based Neural Networks"},{"key":"B6","doi-asserted-by":"publisher","first-page":"3169","DOI":"10.3390\/app9153169","article-title":"A survey of handwritten character recognition with MNIST and EMNIST","volume":"2019","author":"Baldominos","year":"2019","journal-title":"Appl. Sci."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1162\/neco.1995.7.6.1129","article-title":"An information-maximization approach to blind separation and blind deconvolution","volume":"7","author":"Bell","year":"1995","journal-title":"Neural Comput."},{"journal-title":"Bayesian Theory","year":"2000","author":"Bernardo","key":"B8"},{"key":"B9","doi-asserted-by":"publisher","first-page":"494","DOI":"10.1016\/j.conb.2010.07.009","article-title":"The single dendritic branch as a fundamental functional unit in the nervous system","volume":"20","author":"Branco","year":"2010","journal-title":"Curr. Opin. Neurobiol."},{"key":"B10","doi-asserted-by":"crossref","first-page":"2921","DOI":"10.1109\/IJCNN.2017.7966217","article-title":"\u201cEMNIST: extending MNIST to handwritten letters,\u201d","author":"Cohen","year":"2017","journal-title":"2017 International Joint Conference on Neural Networks (IJCNN)"},{"key":"B11","unstructured":"Online passive-aggressive algorithms551585 CrammerK. DekelO. KeshetJ. Shalev-ShwartzS. SingerY. J. Mach. Learn. Res.72006"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e68422","DOI":"10.7554\/eLife.68422","article-title":"Global organization of neuronal activity only requires unstructured local connectivity","volume":"11","author":"Dahmen","year":"2022","journal-title":"eLife"},{"key":"B13","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","article-title":"Loihi: a neuromorphic manycore processor with on-chip learning","volume":"38","author":"Davies","year":"2018","journal-title":"IEEE Micro"},{"key":"B14","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The MNIST database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag."},{"journal-title":"Statistics for Engine Optimization","year":"2000","author":"Edwards","key":"B15"},{"key":"B16","doi-asserted-by":"publisher","first-page":"1437","DOI":"10.1016\/j.neunet.2004.07.003","article-title":"Sparse distributed memory using N-of-M codes","volume":"17","author":"Furber","year":"2004","journal-title":"Neural Netw."},{"journal-title":"SpiNNaker: A Spiking Neural Network Architecture","year":"2020","author":"Furber","key":"B17"},{"key":"B18","doi-asserted-by":"publisher","first-page":"648","DOI":"10.1109\/TNN.2006.890804","article-title":"Sparse distributed memory using rank-order neural codes","volume":"18","author":"Furber","year":"2007","journal-title":"IEEE Trans. Neural Netw."},{"key":"B19","doi-asserted-by":"publisher","first-page":"132","DOI":"10.1016\/j.neuron.2010.12.008","article-title":"The dendritic branch is the preferred integrative unit for protein synthesis-dependent LTP","volume":"69","author":"Govindarajan","year":"2011","journal-title":"Neuron"},{"key":"B20","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"\u201cDeep residual learning for image recognition,\u201d","author":"He","year":"2016","journal-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B21","doi-asserted-by":"publisher","first-page":"20180007","DOI":"10.1098\/rsfs.2018.0007","article-title":"Spiking neural networks for computer vision","volume":"8","author":"Hopkins","year":"2018","journal-title":"Interface Focus"},{"key":"B22","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511790423","author":"Jaynes","year":"2003","journal-title":"Probability Theory: The Logic of Science"},{"journal-title":"Sparse Distributed Memory","year":"1988","author":"Kanerva","key":"B23"},{"key":"B24","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.pneurobio.2014.12.002","article-title":"Synaptic clustering within dendrites: an emerging theory of memory formation","volume":"126","author":"Kastellakis","year":"2015","journal-title":"Prog. Neurobiol."},{"key":"B25","doi-asserted-by":"publisher","first-page":"321","DOI":"10.1016\/j.conb.2008.08.013","article-title":"Synaptic clustering by dendritic signalling mechanisms","volume":"18","author":"Larkum","year":"2008","journal-title":"Curr. Opin. Neurobiol."},{"key":"B26","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"46","author":"LeCun","year":"1998","journal-title":"Proc. IEEE"},{"key":"B27","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.neunet.2005.01.002","article-title":"Improved local learning rule for information maximization and related applications","volume":"18","author":"Linsker","year":"2005","journal-title":"Neural Netw."},{"key":"B28","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1146\/annurev.neuro.28.061604.135703","article-title":"Dendritic computation","volume":"28","author":"London","year":"2005","journal-title":"Annu. Rev. Neurosci."},{"key":"B29","doi-asserted-by":"publisher","first-page":"860","DOI":"10.1109\/JPROC.2014.2310593","article-title":"Noise as a resource for computation and learning in networks of spiking neurons","volume":"102","author":"Maass","year":"2014","journal-title":"Proc. IEEE"},{"key":"B30","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1016\/j.neuron.2012.10.002","article-title":"The neuronal organization of the retina","volume":"76","author":"Masland","year":"2012","journal-title":"Neuron"},{"key":"B31","doi-asserted-by":"publisher","first-page":"14634","DOI":"10.1038\/s41598-021-93977-0","article-title":"Efficient-CapsNet: capsule network with self-attention routing","volume":"11","author":"Mazzia","year":"2021","journal-title":"Sci. Rep."},{"key":"B32","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1162\/neco.1992.4.4.502","article-title":"NMDA-based pattern discrimination in a modeled cortical neuron","volume":"4","author":"Mel","year":"1992","journal-title":"Neural Comput."},{"journal-title":"Priors for Infinite Networks","year":"1996","author":"Neal","key":"B33"},{"key":"B34","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1109\/TIP.2004.840701","article-title":"Building kernels from binary strings for image matching","volume":"14","author":"Odone","year":"2005","journal-title":"IEEE Trans. Image Process."},{"journal-title":"Kendall's Advanced Theory of Statistics: Bayesian Inference","year":"1994","author":"O'Hagan","key":"B35"},{"key":"B36","doi-asserted-by":"publisher","first-page":"437","DOI":"10.3389\/fnins.2015.00437","article-title":"Converting static image datasets to spiking neuromorphic datasets using saccades","volume":"9","author":"Orchard","year":"2015","journal-title":"Front. Neurosci."},{"key":"B37","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.jphysparis.2013.05.003","article-title":"Coding and decoding with dendrites","volume":"108","author":"Papoutsi","year":"2014","journal-title":"J. Physiol."},{"key":"B38","doi-asserted-by":"publisher","first-page":"819063","DOI":"10.3389\/fnins.2022.819063","article-title":"Liquid state machine on spinnaker for spatio-temporal classification tasks","volume":"16","author":"Pati\u00f1o-Saucedo","year":"2022","journal-title":"Front. Neurosci."},{"key":"B39","unstructured":"PhadkeM. S. Englewood Cliffs, NJPrentice HallQuality Engineering Using Robust Design1989"},{"key":"B40","article-title":"\u201cLocality-sensitive binary codes from shift-invariant kernels,\u201d","author":"Raginsky","year":"2009","journal-title":"Advances in Neural Information Processing Systems"},{"journal-title":"IJCAI International Joint Conference on Artificial Intelligence","article-title":"\u201cStreamed learning: one-pass SVMs,\u201d","year":"2009","key":"B41"},{"journal-title":"Gaussian Processes for Machine Learning.","year":"2006","author":"Rasmussen","key":"B42"},{"journal-title":"Spikes: Exploring the Neural Code","year":"1996","author":"Reike","key":"B43"},{"key":"B44","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.conb.2018.08.003","article-title":"Dendritic solutions to the credit assignment problem","volume":"54","author":"Richards","year":"2019","journal-title":"Curr. Opin. Neurobiol."},{"key":"B45","doi-asserted-by":"publisher","first-page":"101","DOI":"10.5555\/1005332.1005336","article-title":"In defense of one-vs-all classification","volume":"5","author":"Rifkin","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511809682","author":"Shawe-Taylor","year":"2004","journal-title":"Kernel Methods for Pattern Analysis"},{"key":"B47","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1080\/02664768700000020","article-title":"Maximum entropy sampling","volume":"14","author":"Shewry","year":"1987","journal-title":"J. Appl. Stat."},{"key":"B48","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198568315.001.0001","author":"Sivia","year":"2006","journal-title":"Data Analysis - A Bayesian Tutorial, 2nd Edn"},{"key":"B49","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780198745273.001.0001","author":"Stuart","year":"2016","journal-title":"Dendrites"},{"journal-title":"Rank Order Coding","year":"1998","author":"Thorpe","key":"B50"},{"journal-title":"The Information Bottleneck Method","year":"1999","author":"Tishby","key":"B51"},{"key":"B52","first-page":"1750","article-title":"\u201cLarge scale online kernel classification,\u201d","author":"Wang","year":"2013","journal-title":"Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence"},{"key":"B53","unstructured":"Breaking the curse of kernelization: budgeted stochastic gradient descent for large-scale SVM training31033131 WangZ. CrammerK. VuceticS. J. Mach. Learn. Res.132012"},{"key":"B54","unstructured":"WardenP. StewartM. PlancherB. BanburyC. PrakashS. ChenE. Machine learning sensors. arXiv preprint arXiv:2206.032662022"},{"key":"B55","doi-asserted-by":"publisher","first-page":"601109","DOI":"10.3389\/fnins.2021.601109","article-title":"Efficient spike-driven learning with dendritic event-based processing","volume":"15","author":"Yang","year":"","journal-title":"Front. Neurosci."},{"key":"B56","doi-asserted-by":"publisher","first-page":"2801","DOI":"10.1109\/TNNLS.2020.3045492","article-title":"Bicoss: toward large-scale cognition brain with multigranular neuromorphic architecture","volume":"33","author":"Yang","year":"","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"B57","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2015.09.003","article-title":"One-pass online learning: a local approach","volume":"51","author":"Zhou","year":"2016","journal-title":"Pattern Recogn."}],"container-title":["Frontiers in Neuroinformatics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2023.1125844\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,9]],"date-time":"2023-12-09T08:25:00Z","timestamp":1702110300000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fninf.2023.1125844\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,21]]},"references-count":57,"alternative-id":["10.3389\/fninf.2023.1125844"],"URL":"https:\/\/doi.org\/10.3389\/fninf.2023.1125844","relation":{},"ISSN":["1662-5196"],"issn-type":[{"type":"electronic","value":"1662-5196"}],"subject":[],"published":{"date-parts":[[2023,3,21]]},"article-number":"1125844"}}