{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,7,14]],"date-time":"2024-07-14T00:04:30Z","timestamp":1720915470830},"reference-count":54,"publisher":"MIT Press","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Neural Computation"],"published-print":{"date-parts":[[2019,2]]},"abstract":"<jats:p>This work lays the foundation for a framework of cortical learning based on the idea of a competitive column, which is inspired by the functional organization of neurons in the cortex. A column describes a prototypical organization for neurons that gives rise to an ability to learn scale, rotation, and translation-invariant features. This is empowered by a recently developed learning rule, conflict learning, which enables the network to learn over both driving and modulatory feedforward, feedback, and lateral inputs. The framework is further supported by introducing both a notion of neural ambiguity and an adaptive threshold scheme. Ambiguity, which captures the idea that too many decisions lead to indecision, gives the network a dynamic way to resolve locally ambiguous decisions. The adaptive threshold operates over multiple timescales to regulate neural activity under the varied arrival timings of input in a highly interconnected multilayer network with feedforward and feedback. The competitive column architecture is demonstrated on a large-scale (54,000 neurons and 18 million synapses), invariant model of border ownership. The model is trained on four simple, fixed-scale shapes: two squares, one rectangle, and one symmetric L-shape. Tested on 1899 synthetic shapes of varying scale and complexity, the model correctly assigned border ownership with 74% accuracy. The model's abilities were also illustrated on contours of objects taken from natural images. Combined with conflict learning, the competitive column and ambiguity give a better intuitive understanding of how feedback, modulation, and inhibition may interact in the brain to influence activation and learning.<\/jats:p>","DOI":"10.1162\/neco_a_01156","type":"journal-article","created":{"date-parts":[[2018,12,21]],"date-time":"2018-12-21T23:50:52Z","timestamp":1545436252000},"page":"344-387","source":"Crossref","is-referenced-by-count":1,"title":["Learning Invariant Features in Modulatory Networks through Conflict and Ambiguity"],"prefix":"10.1162","volume":"31","author":[{"given":"W. Shane","family":"Grant","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Southern California, Los Angeles, CA 90089, U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurent","family":"Itti","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Department of Psychology and Neuroscience Graduate Program, University of Southern California, Los Angeles, CA 90089, U.S.A."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.161"},{"key":"B2","doi-asserted-by":"crossref","DOI":"10.1093\/oso\/9780198538493.001.0001","author":"Bishop C. M.","year":"1995","journal-title":"Neural networks for pattern recognition"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1038\/321579a0"},{"key":"B4","author":"Bridson R.","year":"2007","journal-title":"Proceedings of the SIGGRAPH O7 ACM"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2005.11.026"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.02.005"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2345401"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00203.2007"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.01.010"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2300479"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/1.1.1"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.4.002379"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1007\/BF00344251"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.01.007"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1101\/162263"},{"key":"B17","first-page":"770","author":"He K.","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1017\/S0952523800009640"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1002\/cne.901580304"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1152\/jn.00394.2013"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1167\/15.16.3"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1038\/srep32672"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"B25","author":"Kogo N.","year":"2014","journal-title":"Neural mechanisms of figure-ground organization: Border-ownership, competition and perceptual switching"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2014.00972"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13276"},{"key":"B28","first-page":"21","author":"Liu W.","year":"2016","journal-title":"Proceedings of the European Conference on Computer Vision"},{"key":"B29","first-page":"97","author":"Long M.","year":"2015","journal-title":"Proceedings of the International Conference on Machine Learning"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.1999.790410"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1002\/cne.23458"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.3590-14.2015"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1014655108"},{"key":"B34","first-page":"5949","volume-title":"Advances in neural information processing systems","volume":"30","author":"Neyshabur B.","year":"2017"},{"key":"B35","author":"Nicholls J. G.","year":"2001","journal-title":"From neuron to brain"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1038\/nn1989"},{"key":"B37","first-page":"779","author":"Redmon J.","year":"2016","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B38","first-page":"91","volume-title":"Advances in neural information processing systems","volume":"28","author":"Ren S.","year":"2015"},{"key":"B39","author":"Rubin E.","year":"1915","journal-title":"Synsoplevede figurer"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.1016\/j.visres.2013.10.005"},{"key":"B41","first-page":"3859","volume-title":"Advances in neural information processing systems","volume":"30","author":"Sabour S.","year":"2017"},{"key":"B42","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.1995.7.2.267"},{"key":"B43","doi-asserted-by":"publisher","DOI":"10.1162\/jocn.2006.18.4.562"},{"key":"B44","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.05.006"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.0700622104"},{"key":"B46","first-page":"994","author":"Serre T.","year":"2005","journal-title":"Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition"},{"key":"B47","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.1037-13.2013"},{"key":"B48","author":"Sun B.","year":"2016","journal-title":"Proceedings of the 30th AAAI Conference on Artificial Intelligence"},{"key":"B49","first-page":"5117","author":"Teo C.","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00025-9"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2008.10.008"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2015.01695"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1523\/ENEURO.0127-16.2016"},{"key":"B54","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1100999108"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.20-17-06594.2000"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/neco_a_01156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,13]],"date-time":"2024-07-13T15:33:35Z","timestamp":1720884815000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/31\/2\/344-387\/8444"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2]]},"references-count":54,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2019,2]]}},"alternative-id":["10.1162\/neco_a_01156"],"URL":"https:\/\/doi.org\/10.1162\/neco_a_01156","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2]]}}}