{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T14:08:28Z","timestamp":1778249308203,"version":"3.51.4"},"reference-count":29,"publisher":"MIT Press - Journals","issue":"3","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>A fundamental aspect of learning in biological neural networks is the plasticity property which allows them to modify their configurations during their lifetime. Hebbian learning is a biologically plausible mechanism for modeling the plasticity property in artificial neural networks (ANNs), based on the local interactions of neurons. However, the emergence of a coherent global learning behavior from local Hebbian plasticity rules is not very well understood. The goal of this work is to discover interpretable local Hebbian learning rules that can provide autonomous global learning. To achieve this, we use a discrete representation to encode the learning rules in a finite search space. These rules are then used to perform synaptic changes, based on the local interactions of the neurons. We employ genetic algorithms to optimize these rules to allow learning on two separate tasks (a foraging and a prey\u2013predator scenario) in online lifetime learning settings. The resulting evolved rules converged into a set of well-defined interpretable types, that are thoroughly discussed. Notably, the performance of these rules, while adapting the ANNs during the learning tasks, is comparable to that of offline learning methods such as hill climbing.<\/jats:p>","DOI":"10.1162\/evco_a_00286","type":"journal-article","created":{"date-parts":[[2020,12,22]],"date-time":"2020-12-22T16:48:41Z","timestamp":1608655721000},"page":"391-414","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":9,"title":["Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions"],"prefix":"10.1162","volume":"29","author":[{"given":"Anil","family":"Yaman","sequence":"first","affiliation":[{"name":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, 5612 AP, the NetherlandsDepartment of Bio and Brain Engineering, Korea Advanced Institute of Science and Technology, Daejeon, 34141, Republic of Korea anilyaman@kaist.ac.kr"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giovanni","family":"Iacca","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, Trento, 38122, Italy giovanni.iacca@unitn.it"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Decebal Constantin","family":"Mocanu","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, 5612 AP, the NetherlandsFaculty of Electrical Engineering, Mathematics and Computer Science, University of Twente, Enschede, 7522NB, the Netherlands d.c.mocanu@utwente.nl"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Matt","family":"Coler","sequence":"additional","affiliation":[{"name":"Campus Frysl\u00e2n, University of Groningen, Leeuwarden, 8911 AE, the Netherlands m.coler@rug.nl"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"George","family":"Fletcher","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, 5612 AP, the Netherlands g.h.l.fletcher@tue.nl"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mykola","family":"Pechenizkiy","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Computer Science, Eindhoven University of Technology, Eindhoven, 5612 AP, the Netherlands m.pechenizkiy@tue.nl"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2021,9,1]]},"reference":[{"issue":"1","key":"2021090111591922000_B1","doi-asserted-by":"crossref","first-page":"475","DOI":"10.1146\/annurev.ne.13.030190.002355","article-title":"Hebbian synapses: Biophysical mechanisms and algorithms","volume":"13","author":"Brown","year":"1990","journal-title":"Annual Review of Neuroscience"},{"key":"2021090111591922000_B2","first-page":"326","volume-title":"Australasian Joint Conference on Artificial Intelligence","author":"Coleman","year":"2012"},{"key":"2021090111591922000_B3","doi-asserted-by":"crossref","DOI":"10.1201\/9781420011449","volume-title":"Fundamentals of natural computing: Basic concepts, algorithms, and applications","author":"De Castro","year":"2006"},{"issue":"6395","key":"2021090111591922000_B4","doi-asserted-by":"crossref","first-page":"1349","DOI":"10.1126\/science.aao0862","article-title":"Locally coordinated synaptic plasticity of visual cortex neurons in vivo","volume":"360","author":"El-Boustani","year":"2018","journal-title":"Science"},{"issue":"1","key":"2021090111591922000_B5","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1007\/s12065-007-0002-4","article-title":"Neuroevolution: From architectures to learning","volume":"1","author":"Floreano","year":"2008","journal-title":"Evolutionary Intelligence"},{"issue":"4-5","key":"2021090111591922000_B6","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/S0893-6080(00)00032-0","article-title":"Evolutionary robots with on-line self-organization and behavioral fitness","volume":"13","author":"Floreano","year":"2000","journal-title":"Neural Networks"},{"key":"2021090111591922000_B7","volume-title":"Genetic algorithms in search, optimization and machine learning","author":"Goldberg","year":"1989"},{"key":"2021090111591922000_B8","volume-title":"The organization of behavior: A neuropsychological theory","author":"Hebb","year":"1949"},{"key":"2021090111591922000_B9","first-page":"1","article-title":"Artificial neurogenesis: An introduction and selective review.","author":"Kowaliw","year":"2014","journal-title":"Growing adaptive machines"},{"key":"2021090111591922000_B10","first-page":"152:27","article-title":"Biological context of Hebb learning in artificial neural networks, a review.","author":"Kuriscak","year":"2015","journal-title":"Neurocomputing"},{"issue":"1","key":"2021090111591922000_B11","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-018-04316-3","article-title":"Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science","volume":"9","author":"Mocanu","year":"2018","journal-title":"Nature Communications"},{"key":"2021090111591922000_B12","first-page":"251","article-title":"Artificial evolution of plastic neural networks: A few key concepts","author":"Tonelli","year":"2014","journal-title":"Growing adaptive machines"},{"issue":"1","key":"2021090111591922000_B13","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1177\/1059-712302-010001-01","article-title":"Evolution of reinforcement learning in uncertain environments: A simple explanation for complex foraging behaviors","volume":"10","author":"Niv","year":"2002","journal-title":"Adaptive Behavior"},{"key":"2021090111591922000_B14","doi-asserted-by":"crossref","first-page":"146","DOI":"10.1109\/FPA.1994.636092","volume-title":"Proceedings of From Perception to Action Conference","author":"Nolfi","year":"1994"},{"key":"2021090111591922000_B15","first-page":"4688","volume-title":"International Joint Conference on Neural Networks","author":"Orchard","year":"2016"},{"key":"2021090111591922000_B16","first-page":"113:54","article-title":"Continual lifelong learning with neural networks: A review","author":"Parisi","year":"2019","journal-title":"Neural Networks"},{"key":"2021090111591922000_B17","first-page":"533","volume-title":"International Conference on Simulation of Adaptive Behavior","author":"Risi","year":"2010"},{"issue":"6088","key":"2021090111591922000_B18","doi-asserted-by":"crossref","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"1986","journal-title":"Nature"},{"key":"2021090111591922000_B19","first-page":"59","volume-title":"IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks","author":"Runarsson","year":"2000"},{"key":"2021090111591922000_B20","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/B978-0-12-148955-7.50010-2","article-title":"The Hebb rule for synaptic plasticity: Algorithms and implementations","author":"Sejnowski","year":"1989","journal-title":"Neural models of plasticity"},{"issue":"1","key":"2021090111591922000_B21","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1109\/4235.585894","article-title":"A phylogenetic, ontogenetic, and epigenetic view of bio-inspired hardware systems","volume":"1","author":"Sipper","year":"1997","journal-title":"IEEE Transactions on Evolutionary Computation"},{"key":"2021090111591922000_B22","first-page":"569","volume-title":"International Conference on Artificial Life","author":"Soltoggio","year":"2008"},{"key":"2021090111591922000_B23","first-page":"34:28","author":"Soltoggio","year":"2012","journal-title":"From modulated Hebbian plasticity to simple behavior learning through noise and weight saturation"},{"key":"2021090111591922000_B24","first-page":"108:48","article-title":"Born to learn: The inspiration, progress, and future of evolved plastic artificial neural networks","author":"Soltoggio","year":"2018","journal-title":"Neural Networks"},{"key":"2021090111591922000_B25","first-page":"2563","volume-title":"International Joint Conference on Neural Networks","author":"Vasilkoski","year":"2011"},{"issue":"6","key":"2021090111591922000_B26","doi-asserted-by":"crossref","first-page":"80","DOI":"10.2307\/3001968","article-title":"Individual comparisons by ranking methods","volume":"1","author":"Wilcoxon","year":"1945","journal-title":"Biometrics Bulletin"},{"key":"2021090111591922000_B27","volume-title":"Genetic and Evolutionary Computation Conference, 13-17 July 2019, Prague, Czech Republic","author":"Yaman","year":"2019"},{"key":"2021090111591922000_B28","volume-title":"Genetic and Evolutionary Computation Conference, 15-19 July 2018, Kyoto, Japan","author":"Yaman","year":"2018"},{"issue":"9","key":"2021090111591922000_B29","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1109\/5.784219","article-title":"Evolving artificial neural networks","volume":"87","author":"Yao","year":"1999","journal-title":"Proceedings of the IEEE"}],"container-title":["Evolutionary Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/evco\/article-pdf\/29\/3\/391\/1959467\/evco_a_00286.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/evco\/article-pdf\/29\/3\/391\/1959467\/evco_a_00286.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T11:59:58Z","timestamp":1630497598000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/evco\/article\/29\/3\/391\/97351\/Evolving-Plasticity-for-Autonomous-Learning-under"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":29,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,9,1]]},"published-print":{"date-parts":[[2021,9,1]]}},"URL":"https:\/\/doi.org\/10.1162\/evco_a_00286","relation":{},"ISSN":["1530-9304"],"issn-type":[{"value":"1530-9304","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021]]},"published":{"date-parts":[[2021]]}}}