{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:45:32Z","timestamp":1761896732895},"reference-count":85,"publisher":"MIT Press","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2018,5]]},"abstract":"<jats:p>Finding actions that satisfy the constraints imposed by both external inputs and internal representations is central to decision making. We demonstrate that some important classes of constraint satisfaction problems (CSPs) can be solved by networks composed of homogeneous cooperative-competitive modules that have connectivity similar to motifs observed in the superficial layers of neocortex. The winner-take-all modules are sparsely coupled by programming neurons that embed the constraints onto the otherwise homogeneous modular computational substrate. We show rules that embed any instance of the CSP's planar four-color graph coloring, maximum independent set, and sudoku on this substrate and provide mathematical proofs that guarantee these graph coloring problems will convergence to a solution. The network is composed of nonsaturating linear threshold neurons. Their lack of right saturation allows the overall network to explore the problem space driven through the unstable dynamics generated by recurrent excitation. The direction of exploration is steered by the constraint neurons. While many problems can be solved using only linear inhibitory constraints, network performance on hard problems benefits significantly when these negative constraints are implemented by nonlinear multiplicative inhibition. Overall, our results demonstrate the importance of instability rather than stability in network computation and offer insight into the computational role of dual inhibitory mechanisms in neural circuits.<\/jats:p>","DOI":"10.1162\/neco_a_01074","type":"journal-article","created":{"date-parts":[[2018,3,22]],"date-time":"2018-03-22T21:42:04Z","timestamp":1521754924000},"page":"1359-1393","source":"Crossref","is-referenced-by-count":14,"title":["Solving Constraint-Satisfaction Problems with Distributed Neocortical-Like Neuronal Networks"],"prefix":"10.1162","volume":"30","author":[{"given":"Ueli","family":"Rutishauser","sequence":"first","affiliation":[{"name":"Computation and Neural Systems, Division of Biology and Biological Engineering, California Institute of Technology, Pasadena, CA 91125, U.S.A., and Cedars-Sinai Medical Center, Departments of Neurosurgery, Neurology and Biomedical Sciences, Los Angeles, CA 90048, U.S.A."}]},{"given":"Jean-Jacques","family":"Slotine","sequence":"additional","affiliation":[{"name":"Nonlinear Systems Laboratory, Department of Mechanical Engineering and Department of Brain and Cognitive Sciences, MIT, Cambridge, MA 02139, U.S.A."}]},{"given":"Rodney J.","family":"Douglas","sequence":"additional","affiliation":[{"name":"Institute of Neuroinformatics, University and ETH Zurich, Zurich 8057, Switzerland"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1017\/S0033583500003024"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1126\/science.1193210"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1142\/S0218127404009806"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1215\/ijm\/1256049011"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.3389\/fncir.2012.00118"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.92.9.3844"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1400-04.2004"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/0006-8993(74)90375-8"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1038\/30735"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2014.01.005"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1038\/nrn3136"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.01.031.2008"},{"key":"B13","volume-title":"Theoretical neuroscience","author":"Dayan P.","year":"2001"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-4903-1_5"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1991.sp018733"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.27.070203.144152"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2007.04.024"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.4.480"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1991.sp018730"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms6689"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1038\/srep00725"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(92)90004-3"},{"key":"B23","volume-title":"A practical guide to heavy tails: Statistical techniques and applications","author":"Feldman R.","year":"1998"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1038\/380249a0"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.05.015"},{"key":"B26","author":"Gleich D. F.","year":"2009","journal-title":"Models and algorithms for pagerank sensitivity"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1023\/A:1006314320276"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003311"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1038\/11219"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1038\/35016072"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1619788114"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.79.8.2554"},{"issue":"3","key":"B33","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1007\/BF00339943","volume":"52","author":"Hopfield J.","year":"1985","journal-title":"Biological Cybernetics"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511810817"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-008-9003-6"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2011.09.027"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3305"},{"key":"B38","volume":"30","author":"Jonke Z.","year":"2016","journal-title":"Front. Neurosci."},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1038\/nn0817-1189d"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4684-2001-2_9"},{"key":"B41","doi-asserted-by":"crossref","unstructured":"Koch, C. (1998). Biophysics of computation: Information processing in single neurons. New York: Oxford University Press.","DOI":"10.1093\/oso\/9780195104912.001.0001"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.80.9.2799"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2007.04.005"},{"issue":"1","key":"B44","first-page":"32","volume":"13","author":"Kumar V.","year":"1992","journal-title":"AI Magazine"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1038\/nature17192"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3494"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3488"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1002\/9781118927601"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1002\/aic.690460317"},{"key":"B51","volume-title":"Distributed algorithms","author":"Lynch N. A.","year":"1996"},{"key":"B52","author":"Maas A. L.","year":"2013","journal-title":"Proceedings of the 30th International Conference on Machine Learning"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300014827"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1111\/cogs.12146"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1126\/science.1254642"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jphysparis.2009.05.013"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.2.167"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1162\/089976699300016782"},{"key":"B59","first-page":"719","volume-title":"Advances in neural information processing systems","volume":"26","author":"Mostafa H.","year":"2013"},{"key":"B60","first-page":"807","volume-title":"Proceedings of the 27th International Conference on Machine Learning","author":"Nair V.","year":"2010"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1212083110"},{"key":"B62","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00182"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.614341"},{"key":"B64","doi-asserted-by":"publisher","DOI":"10.1038\/nature12676"},{"key":"B66","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2015.00141"},{"key":"B67","doi-asserted-by":"publisher","DOI":"10.1145\/237814.238005"},{"key":"B68","volume-title":"Jflap\u2014An interactive formal languages and automata package","author":"Rodger S.","year":"2006"},{"key":"B69","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1976.4309519"},{"key":"B70","volume-title":"Taking sudoku seriously: The math behind the world's most popular pencil puzzle","author":"Rosenhouse J.","year":"2011"},{"key":"B71","doi-asserted-by":"publisher","DOI":"10.1002\/dneu.20853"},{"key":"B72","volume-title":"Artificial intelligence: A modern approach (international ed.)","author":"Russell S. J.","year":"2010","edition":"3"},{"key":"B73","doi-asserted-by":"publisher","DOI":"10.1162\/neco.2008.03-08-734"},{"key":"B74","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00091"},{"key":"B75","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00304"},{"key":"B76","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1004039"},{"key":"B77","unstructured":"Siek, J. G., Lee, L.Q. & Lumsdaine, A. (2002). The Boost Graph Library: User guide and reference manual. Boston, MA: Addison-Wesley Longman."},{"key":"B78","doi-asserted-by":"publisher","DOI":"10.1002\/acs.754"},{"key":"B79","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4157"},{"key":"B80","doi-asserted-by":"publisher","DOI":"10.3389\/fncel.2015.00067"},{"key":"B81","first-page":"295","volume-title":"Proceedings of the Second International Conference on Artificial Neural Networks","author":"Wang C. J.","year":"1991"},{"key":"B82","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2005.04.012"},{"key":"B83","doi-asserted-by":"publisher","DOI":"10.1162\/089976601300014574"},{"key":"B84","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2014.09.064"},{"key":"B85","first-page":"1228","volume-title":"The handbook of brain theory and neural networks","author":"Yuille A.","year":"2003"},{"key":"B86","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2013.00056"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_01074","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,16]],"date-time":"2022-08-16T19:26:23Z","timestamp":1660677983000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/30\/5\/1359-1393\/8351"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5]]},"references-count":85,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2018,5]]}},"alternative-id":["10.1162\/neco_a_01074"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_01074","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5]]}}}