{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T04:57:43Z","timestamp":1760245063907},"reference-count":31,"publisher":"MIT Press - Journals","issue":"10","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,9,16]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The transformation of synaptic input into action potential in nerve cells is strongly influenced by the morphology of the dendritic arbor as well as the synaptic efficacy map. The multiplicity of dendritic branches strikingly enables a single cell to act as a highly nonlinear processing element. Studies have also found functional synaptic clustering whereby synapses that encode a common sensory feature are spatially clustered together on the branches. Motivated by these findings, here we introduce a multibranch formal model of the neuron that can integrate synaptic inputs nonlinearly through collective action of its dendritic branches and yields synaptic clustering. An analysis in support of its use as a computational building block is offered. Also offered is an accompanying gradient descent\u2013based learning algorithm. The model unit spans a wide spectrum of nonlinearities, including the parity problem, and can outperform the multilayer perceptron in generalizing to unseen data. The occurrence of synaptic clustering boosts the generalization efficiency of the unit, which may also be the answer for the puzzling ubiquity of synaptic clustering in the real neurons. Our theoretical analysis is backed up by simulations. The study could pave the way to new artificial neural networks.<\/jats:p>","DOI":"10.1162\/neco_a_01428","type":"journal-article","created":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T20:45:18Z","timestamp":1626727518000},"page":"2736-2761","update-policy":"http:\/\/dx.doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":1,"title":["Multibranch Formal Neuron: An Internally Nonlinear Learning Unit"],"prefix":"10.1162","volume":"33","author":[{"given":"Marifi","family":"G\u00fcler","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Eastern Mediterranean University, 99628 Famagusta North Cyprus, via Mersin 10, Turkey marifi.guler@gmail.com"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"281","published-online":{"date-parts":[[2021,9,16]]},"reference":[{"key":"2021091622573494800_B1","doi-asserted-by":"crossref","first-page":"2991","DOI":"10.1002\/jnr.22444","article-title":"The decade of the dendritic NMDA spike","volume":"88","author":"Antic","year":"2010","journal-title":"Journal of Neuroscience Research"},{"key":"2021091622573494800_B2","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.conb.2017.08.013","article-title":"Modelling plasticity in dendrites: From single cells to networks","volume":"46","author":"Bono","year":"2017","journal-title":"Current Opinion in Neurobiology"},{"key":"2021091622573494800_B3","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1016\/j.brainresrev.2008.12.023","article-title":"Activity-dependent structural plasticity","volume":"60","author":"Butz","year":"2009","journal-title":"Brain Research Review"},{"key":"2021091622573494800_B4","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1000886","article-title":"Stochastic ion channel gating in dendritic neurons: Morphology dependence and probabilistic synaptic activation of dendritic spikes","volume":"6","author":"Cannon","year":"2010","journal-title":"PLOS Computational Biology"},{"key":"2021091622573494800_B5","doi-asserted-by":"crossref","first-page":"782","DOI":"10.1038\/nature03012","article-title":"Cortical rewiring and information storage","volume":"431","author":"Chklovskii","year":"2004","journal-title":"Nature"},{"key":"2021091622573494800_B6","doi-asserted-by":"crossref","first-page":"180","DOI":"10.1038\/nature14251","article-title":"Branch-specific dendritic Ca2+ spikes cause persistent synaptic plasticity","volume":"520","author":"Cichon","year":"2015","journal-title":"Nature"},{"key":"2021091622573494800_B7","unstructured":"Dua, D., & Graff, C. (2019). UCI Machine Learning Repository. Irvine: University of California, School of Information and Computer Science. http:\/\/archive.ics.uci.edu\/ml"},{"key":"2021091622573494800_B8","doi-asserted-by":"crossref","DOI":"10.1038\/nrn1937","article-title":"A clustered plasticity model of long-term memory engrams","volume":"7","author":"Govindarajan","year":"2006","journal-title":"Nature Reviews Neuroscience"},{"key":"2021091622573494800_B9","doi-asserted-by":"crossref","first-page":"495","DOI":"10.1016\/S0893-6080(01)00033-8","article-title":"A model with an intrinsic property of learning higher order correlations","volume":"14","author":"G\u00fcler","year":"2001","journal-title":"Neural Networks"},{"key":"2021091622573494800_B10","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1007\/s10827-011-0337-9","article-title":"Persistent membranous cross correlations due to the multiplicity of gates in ion channels","volume":"31","author":"G\u00fcler","year":"2011","journal-title":"Journal of Computational Neuroscience"},{"key":"2021091622573494800_B11","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1162\/NECO_a_00384","article-title":"Stochastic Hodgkin-Huxley equations with colored noise terms in the conductances","volume":"25","author":"G\u00fcler","year":"2013","journal-title":"Neural Computation"},{"key":"2021091622573494800_B12","doi-asserted-by":"crossref","DOI":"10.1103\/PhysRevE.91.062116","article-title":"Minimal diffusion formulation of Markov chain ensembles and its application to ion channel clusters","volume":"91","author":"G\u00fcler","year":"2015","journal-title":"Physical Review E"},{"key":"2021091622573494800_B13","doi-asserted-by":"crossref","unstructured":"G\u00fcler, M.\n           (2021). Reduction of the diffusion equations of ion channel clusters with virtually no increase in the error bound.Fluctuation and Noise Letters, 20(4), 2150035.","DOI":"10.1142\/S0219477521500358"},{"key":"2021091622573494800_B14","doi-asserted-by":"crossref","first-page":"880","DOI":"10.1038\/35104061","article-title":"Dentritic spines: Structure, dynamics and regulation","volume":"2","author":"Hering","year":"2001","journal-title":"Nature Reviews Neuroscience"},{"key":"2021091622573494800_B15","doi-asserted-by":"crossref","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","article-title":"Approximation capabilities of multilayer feedforward networks","volume":"4","author":"Hornik","year":"1991","journal-title":"Neural Networks"},{"key":"2021091622573494800_B16","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1016\/j.tins.2008.03.004","article-title":"Active dendrites: Colorful wings of the mysterious butterflies","volume":"31","author":"Johnston","year":"2008","journal-title":"Trends in Neuroscience"},{"key":"2021091622573494800_B17","doi-asserted-by":"crossref","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":"Progress in Neurobiology"},{"issue":"1","key":"2021091622573494800_B18","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1007\/BF00337288","article-title":"Self-organized formation of topologically correct feature maps","volume":"43","author":"Kohonen","year":"1982","journal-title":"Biological Cybernetics"},{"key":"2021091622573494800_B19","doi-asserted-by":"crossref","first-page":"756","DOI":"10.1126\/science.1171958","article-title":"Synaptic integration in tuft dendrites of layer 5 pyramidal neurons: A new unifying principle","volume":"325","author":"Larkum","year":"2009","journal-title":"Science"},{"key":"2021091622573494800_B20","doi-asserted-by":"crossref","first-page":"13214","DOI":"10.1073\/pnas.0604691103","article-title":"Spontaneous and evoked synaptic rewiring in the neonatal neocortex","volume":"103","author":"Le B\u00e9","year":"2006","journal-title":"Proceedings of the National Academy of Sciences USA"},{"key":"2021091622573494800_B21","doi-asserted-by":"crossref","first-page":"10787","DOI":"10.1523\/JNEUROSCI.5684-10.2011","article-title":"Branch specific plasticity enables self organization of nonlinear computation in single neurons","volume":"31","author":"Legenstein","year":"2011","journal-title":"Journal of Neuroscience"},{"key":"2021091622573494800_B22","doi-asserted-by":"crossref","DOI":"10.3389\/fncom.2020.00057","article-title":"Emergence of stable synaptic clusters on dendrites through synaptic rewiring","volume":"14","author":"Limbacher","year":"2020","journal-title":"Frontiers in Computational Neuroscience"},{"key":"2021091622573494800_B23","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1146\/annurev.neuro.28.061604.135703","article-title":"Dendritic computation","volume":"28","author":"London","year":"2005","journal-title":"Annual Review of Neuroscience"},{"key":"2021091622573494800_B24","doi-asserted-by":"crossref","unstructured":"Maass, W.\n           (1994). Perspectives of current research about the complexity of learning in neural nets. In V.Roychowdhury, K.Siu, & A.Orlitsky (Eds.), Theoretical advances in neural computation and learning (pp. 295\u2013336). Amsterdam: Kluwer.","DOI":"10.1007\/978-1-4615-2696-4_8"},{"key":"2021091622573494800_B25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1146\/annurev-neuro-062111-150343","article-title":"Active properties of neocortical pyramidal neuron dendrites","volume":"36","author":"Major","year":"2013","journal-title":"Annual Review of Neuroscience"},{"key":"2021091622573494800_B26","doi-asserted-by":"crossref","first-page":"761","DOI":"10.1038\/nature02617","article-title":"Structural basis of long-term potentiation in single dendritic spines","volume":"429","author":"Matsuzaki","year":"2004","journal-title":"Nature"},{"key":"2021091622573494800_B27","doi-asserted-by":"crossref","first-page":"2717","DOI":"10.1007\/s11063-019-10051-7","article-title":"Increasing capacity of association memory by means of synaptic clustering","volume":"50","author":"Osaulenko","year":"2019","journal-title":"Neural Processing Letters"},{"key":"2021091622573494800_B28","first-page":"540","article-title":"Tighter bounds of the VC-dimension of three-layer networks","volume":"2","author":"Sakurai","year":"1993","journal-title":"Proceedings of World Congress on Neural Networks"},{"key":"2021091622573494800_B29","doi-asserted-by":"crossref","DOI":"10.3389\/fncel.2015.00067","article-title":"Contribution of sublinear and supralinear dendritic integration to neuronal computations","volume":"9","author":"Tran-Van-Minh","year":"2015","journal-title":"Frontiers in Cellular Neuroscience"},{"key":"2021091622573494800_B30","unstructured":"Weigend, A. S., Rumelhart, D. E., & Huberman, B. A. (1990). Backpropagation, weight elimination, and time series prediction. In Proc. 1990 Connectionist Models Summer School, 65\u201380."},{"key":"2021091622573494800_B31","doi-asserted-by":"crossref","first-page":"749","DOI":"10.1016\/j.neuron.2004.11.011","article-title":"Shrinkage of dendritic spines associated with long-term depression of hippocampal synapses","volume":"44","author":"Zhou","year":"2004","journal-title":"Neuron"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/neco\/article-pdf\/33\/10\/2736\/1963320\/neco_a_01428.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/neco\/article-pdf\/33\/10\/2736\/1963320\/neco_a_01428.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,16]],"date-time":"2021-09-16T22:58:32Z","timestamp":1631833112000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/33\/10\/2736\/103012\/Multibranch-Formal-Neuron-An-Internally-Nonlinear"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,16]]},"references-count":31,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,9,16]]},"published-print":{"date-parts":[[2021,9,16]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01428","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,10]]},"published":{"date-parts":[[2021,9,16]]}}}