{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:01:32Z","timestamp":1771876892347,"version":"3.50.1"},"reference-count":53,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T00:00:00Z","timestamp":1651104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2022,4,28]],"date-time":"2022-04-28T00:00:00Z","timestamp":1651104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"IONOS-ERC","award":["773228"],"award-info":[{"award-number":["773228"]}]},{"name":"Fonds de Recherche du Qu\u00e9bec\u2014Nature et Technologies","award":["287330"],"award-info":[{"award-number":["287330"]}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"crossref","award":["559730"],"award-info":[{"award-number":["559730"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Neuromorph. Comput. Eng."],"published-print":{"date-parts":[[2022,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Backpropagation algorithms on recurrent artificial neural networks require an unfolding of accumulated states over time. These states must be kept in memory for an undefined period of time which is task-dependent and costly for edge devices. This paper uses the reservoir computing paradigm where an untrained recurrent pool of neurons is used as a preprocessor for temporally structured inputs and with a limited number of training data samples. These so-called reservoirs usually require either extensive fine-tuning or neuroplasticity. We propose a new local and unsupervised plasticity rule named P-CRITICAL designed for automatic reservoir tuning that translates well to physical and digital neuromorphic processors. The spiking neuronal architecture implementation is simulated on the Loihi research chip from Intel and on a conventional CPU. Comparisons on state-of-the-art machine learning datasets are given. Improved performance on visual and auditory tasks are observed. There is no need to <jats:italic>a priori<\/jats:italic> tune the reservoir when switching between tasks, making this approach suitable for physical implementations. Furthermore, such plastic behaviour of the reservoir is a key to end-to-end energy-efficient neuromorphic-based machine learning on edge devices.<\/jats:p>","DOI":"10.1088\/2634-4386\/ac6533","type":"journal-article","created":{"date-parts":[[2022,4,7]],"date-time":"2022-04-07T22:15:40Z","timestamp":1649369740000},"page":"024007","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["P-CRITICAL: a reservoir autoregulation plasticity rule for neuromorphic hardware"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6730-0794","authenticated-orcid":true,"given":"Ismael","family":"Balafrej","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9591-220X","authenticated-orcid":false,"given":"Fabien","family":"Alibart","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9306-426X","authenticated-orcid":false,"given":"Jean","family":"Rouat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2022,4,28]]},"reference":[{"key":"nceac6533bib1","first-page":"13","article-title":"The echo state approach to analysing and training recurrent neural networks-with an erratum note, Bonn, Germany: German National Research Center for Information Technology GMD","volume":"vol 148","author":"Jaeger","year":"2001","journal-title":"Technical Report"},{"key":"nceac6533bib2","doi-asserted-by":"publisher","first-page":"2531","DOI":"10.1162\/089976602760407955","article-title":"Real-time computing without stable states: a new framework for neural computation based on perturbations","volume":"14","author":"Maass","year":"2002","journal-title":"Neural Comput."},{"key":"nceac6533bib3","doi-asserted-by":"publisher","first-page":"100","DOI":"10.1016\/j.neunet.2019.03.005","article-title":"Recent advances in physical reservoir computing: a review","volume":"115","author":"Tanaka","year":"2019","journal-title":"Neural Netw."},{"key":"nceac6533bib4","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.neunet.2007.04.017","article-title":"Edge of chaos and prediction of computational performance for neural circuit models","volume":"20","author":"Legenstein","year":"2007","journal-title":"Neural Netw."},{"key":"nceac6533bib5","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1162\/neco.2007.19.1.111","article-title":"Analysis and design of echo state networks","volume":"19","author":"Oztuik","year":"2007","journal-title":"Neural Comput."},{"key":"nceac6533bib6","first-page":"985","article-title":"On the quantification of dynamics in reservoir computing","author":"Verstraeten","year":"2009"},{"key":"nceac6533bib7","first-page":"1","article-title":"Predicting performance using approximate state space model for liquid state machines","author":"Gorad","year":"2019"},{"key":"nceac6533bib8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neunet.2012.07.005","article-title":"Re-visiting the echo state property","volume":"35","author":"Yildiz","year":"2012","journal-title":"Neural Netw."},{"key":"nceac6533bib9","first-page":"658","article-title":"Critical echo state networks","author":"Hajnal","year":"2006"},{"key":"nceac6533bib10","doi-asserted-by":"publisher","first-page":"635","DOI":"10.1093\/jigpal\/jzp043","article-title":"Structure optimization of reservoir networks","volume":"18","author":"Roeschies","year":"2009","journal-title":"Logic J. IGPL"},{"key":"nceac6533bib11","first-page":"811","article-title":"Genetic algorithm for reservoir computing optimization","author":"Ferreira","year":"2009"},{"key":"nceac6533bib12","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.neunet.2012.11.003","article-title":"Effects of synaptic connectivity on liquid state machine performance","volume":"38","author":"Ju","year":"2013","journal-title":"Neural Netw."},{"key":"nceac6533bib13","doi-asserted-by":"crossref","DOI":"10.1109\/IJCNN.2019.8852472","article-title":"Intelligent reservoir generation for liquid state machines using evolutionary optimization","author":"Reynolds","year":"2019"},{"key":"nceac6533bib14","article-title":"A neural architecture search based framework for liquid state machine design","author":"Tian","year":"2020"},{"key":"nceac6533bib15","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.neuroimage.2016.07.051","article-title":"The role of symmetry in neural networks and their Laplacian spectra","volume":"141","author":"de Lange","year":"2016","journal-title":"Neuroimage"},{"key":"nceac6533bib16","first-page":"1","article-title":"Critical branching neural computation","author":"Kello","year":"2010"},{"key":"nceac6533bib17","first-page":"547","article-title":"Regulation toward self-organized criticality in a recurrent spiking neural reservoir","author":"Brodeur","year":"2012"},{"key":"nceac6533bib18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pcbi.1004043","article-title":"Synaptic plasticity enables adaptive self-tuning critical networks","volume":"11","author":"Stepp","year":"2015","journal-title":"PLoS Comput. Biol."},{"key":"nceac6533bib19","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":"nceac6533bib20","article-title":"PyTorch: an imperative style, high-performance deep learning library","volume":"vol 32","author":"Paszke","year":"2019"},{"key":"nceac6533bib21","first-page":"2414","article-title":"Robustness of a memristor based liquid state machine","author":"Soures","year":"2017"},{"key":"nceac6533bib22","article-title":"Classification of auditory stimuli from EEG signals with a regulated recurrent neural network reservoir","author":"Moinnereau","year":"2018"},{"key":"nceac6533bib23","first-page":"88","article-title":"Improving liquid state machine in temporal pattern classification","author":"Luo","year":"2018"},{"key":"nceac6533bib24","doi-asserted-by":"publisher","first-page":"686","DOI":"10.3389\/fnins.2019.00686","article-title":"Deep liquid state machines with neural plasticity for video activity recognition","volume":"13","author":"Soures","year":"2019","journal-title":"Front. Neurosci."},{"key":"nceac6533bib25","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/978-3-030-01418-6_21","article-title":"Learning continuous muscle control for a multi-joint arm by extending proximal policy optimization with a liquid state machine","author":"Tieck","year":"2018"},{"key":"nceac6533bib26","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1109\/jetcas.2019.2934939","article-title":"Enabling non-Hebbian learning in recurrent spiking neural processors with hardware-friendly on-chip intrinsic plasticity","volume":"9","author":"Liu","year":"2019","journal-title":"IEEE J. Emerg. Sel. Top. Circuits Syst."},{"key":"nceac6533bib27","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1007\/s12559-017-9467-3","article-title":"Reservoir computing with both neuronal intrinsic plasticity and multi-clustered structure","volume":"9","author":"Xue","year":"2017","journal-title":"Cogn. Comput."},{"key":"nceac6533bib28","first-page":"55","article-title":"SSO-LSM: a sparse and self-organizing architecture for liquid state machine based neural processors","author":"Jin","year":"2016"},{"key":"nceac6533bib29","first-page":"126","article-title":"Echo in a small-world reservoir: time-series prediction using an economical recurrent neural network","author":"Kawai","year":"2018\/2017"},{"key":"nceac6533bib30","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.neunet.2019.01.002","article-title":"A small-world topology enhances the echo state property and signal propagation in reservoir computing","volume":"112","author":"Kawai","year":"2019","journal-title":"Neural Netw."},{"key":"nceac6533bib31","first-page":"245","article-title":"Stability and topology in reservoir computing","volume":"6438 LNAI","author":"Manevitz","year":"2010"},{"key":"nceac6533bib32","doi-asserted-by":"publisher","first-page":"1364","DOI":"10.1109\/tnn.2007.894082","article-title":"Collective behavior of a small-world recurrent neural system with scale-free distribution","volume":"18","author":"Deng","year":"2007","journal-title":"IEEE Trans. Neural Netw."},{"key":"nceac6533bib33","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1162\/089976604323057443","article-title":"Real-time computation at the edge of chaos in recurrent neural networks","volume":"16","author":"Bertschinger","year":"2004","journal-title":"Neural Comput."},{"key":"nceac6533bib34","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.neunet.2007.04.003","article-title":"An experimental unification of reservoir computing methods","volume":"20","author":"Verstraeten","year":"2007","journal-title":"Neural Netw."},{"key":"nceac6533bib35","first-page":"89","article-title":"Benchmarking reservoir computing on time-independent classification tasks","author":"Alexandre","year":"2009"},{"key":"nceac6533bib36","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1098\/rsta.2007.2092","article-title":"The criticality hypothesis: how local cortical networks might optimize information processing","volume":"366","author":"Beggs","year":"2007","journal-title":"Phil. Trans. R. Soc. A"},{"key":"nceac6533bib37","doi-asserted-by":"publisher","first-page":"108","DOI":"10.3389\/fnsys.2014.00108","article-title":"Spike avalanches in vivo suggest a driven, slightly subcritical brain state","volume":"8","author":"Priesemann","year":"2014","journal-title":"Front. Syst. Neurosci."},{"key":"nceac6533bib38","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1080\/09540090600639339","article-title":"High capacity, small world associative memory models","volume":"18","author":"Davey","year":"2006","journal-title":"Connect. Sci."},{"key":"nceac6533bib39","doi-asserted-by":"publisher","first-page":"504","DOI":"10.3389\/fnins.2019.00504","article-title":"Analysis of liquid ensembles for enhancing the performance and accuracy of liquid state machines","volume":"13","author":"Wijesinghe","year":"2019","journal-title":"Front. Neurosci."},{"key":"nceac6533bib40","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005550","article-title":"Brain network eigenmodes provide a robust and compact representation of the structural connectome in health and disease","volume":"13","author":"Wang","year":"2017","journal-title":"PLoS Comput. Biol."},{"key":"nceac6533bib41","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"nceac6533bib42","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":"nceac6533bib43","doi-asserted-by":"publisher","first-page":"23","DOI":"10.3389\/fnins.2018.00023","article-title":"Feature representations for neuromorphic audio spike streams","volume":"12","author":"Anumula","year":"2018","journal-title":"Front. Neurosci."},{"key":"nceac6533bib44","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1109\/jssc.2010.2085952","article-title":"A QVGA 143 dB dynamic range frame-free PWM image sensor with lossless pixel-level video compression and time-domain CDS","volume":"46","author":"Posch","year":"2011","journal-title":"IEEE J. Solid-State Circuits"},{"key":"nceac6533bib45","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1109\/tcsi.2006.887979","article-title":"A matched silicon cochlea pair with address event representation interface","volume":"54","author":"Chan","year":"2007","journal-title":"IEEE Trans. Circuits Syst. I"},{"key":"nceac6533bib46","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"nceac6533bib47","doi-asserted-by":"publisher","first-page":"e47314","DOI":"10.7554\/eLife.47314.001","article-title":"Brian 2, an intuitive and efficient neural simulator","volume":"8","author":"Stimberg","year":"2019","journal-title":"Elife"},{"key":"nceac6533bib48","first-page":"2282","article-title":"Effective sensor fusion with event-based sensors and deep network architectures","author":"Neil","year":"2016"},{"key":"nceac6533bib49","first-page":"1","article-title":"A timescale Invariant STDP-based spiking deep network for unsupervised online feature Extraction from event-based sensor data","author":"Thiele","year":"2018"},{"key":"nceac6533bib50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3389\/fnins.2019.01085","article-title":"Bio-inspired evolutionary model of spiking neural networks in ionic liquid space","volume":"13","author":"Iranmehr","year":"2019","journal-title":"Front. Neurosci."},{"key":"nceac6533bib51","doi-asserted-by":"crossref","DOI":"10.1109\/ICSIP49896.2020.9339389","article-title":"Exploration of input patterns for enhancing the performance of liquid state machines","author":"Guo","year":"2020"},{"key":"nceac6533bib52","article-title":"On the convergence of Adam and beyond","author":"Reddi","year":"2018"},{"key":"nceac6533bib53","doi-asserted-by":"publisher","first-page":"2635","DOI":"10.1109\/tnnls.2015.2388544","article-title":"A digital liquid state machine with biologically inspired learning and its application to speech recognition","volume":"26","author":"Zhang","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learning Syst."}],"container-title":["Neuromorphic Computing and Engineering"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T07:47:13Z","timestamp":1651736833000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2634-4386\/ac6533"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,28]]},"references-count":53,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,4,28]]},"published-print":{"date-parts":[[2022,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2634-4386\/ac6533","relation":{},"ISSN":["2634-4386"],"issn-type":[{"value":"2634-4386","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,4,28]]},"assertion":[{"value":"P-CRITICAL: a reservoir autoregulation plasticity rule for neuromorphic hardware","name":"article_title","label":"Article Title"},{"value":"Neuromorphic Computing and Engineering","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2021-09-17","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-04-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-04-28","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}