{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,22]],"date-time":"2026-03-22T05:19:35Z","timestamp":1774156775235,"version":"3.50.1"},"reference-count":86,"publisher":"MIT Press","issue":"12","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,11,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>A fundamental challenge at the interface of machine learning and neuroscience is to uncover computational principles that are shared between artificial and biological neural networks. In deep learning, normalization methods such as batch normalization, weight normalization, and their many variants help to stabilize hidden unit activity and accelerate network training, and these methods have been called one of the most important recent innovations for optimizing deep networks. In the brain, homeostatic plasticity represents a set of mechanisms that also stabilize and normalize network activity to lie within certain ranges, and these mechanisms are critical for maintaining normal brain function. In this article, we discuss parallels between artificial and biological normalization methods at four spatial scales: normalization of a single neuron's activity, normalization of synaptic weights of a neuron, normalization of a layer of neurons, and normalization of a network of neurons. We argue that both types of methods are functionally equivalent\u2014that is, both push activation patterns of hidden units toward a homeostatic state, where all neurons are equally used\u2014and we argue that such representations can improve coding capacity, discrimination, and regularization. As a proof of concept, we develop an algorithm, inspired by a neural normalization technique called synaptic scaling, and show that this algorithm performs competitively against existing normalization methods on several data sets. Overall, we hope this bidirectional connection will inspire neuroscientists and machine learners in three ways: to uncover new normalization algorithms based on established neurobiological principles; to help quantify the trade-offs of different homeostatic plasticity mechanisms used in the brain; and to offer insights about how stability may not hinder, but may actually promote, plasticity.<\/jats:p>","DOI":"10.1162\/neco_a_01439","type":"journal-article","created":{"date-parts":[[2021,9,2]],"date-time":"2021-09-02T18:39:55Z","timestamp":1630607995000},"page":"3179-3203","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":23,"title":["A Correspondence Between Normalization Strategies in Artificial and Biological Neural Networks"],"prefix":"10.1162","volume":"33","author":[{"given":"Yang","family":"Shen","sequence":"first","affiliation":[{"name":"Cold Spring Harbor Laboratory, Simons Center for Quantitative Biology, Cold Spring Harbor, NY 11724, U.S.A. yshen@cshl.com"}]},{"given":"Julia","family":"Wang","sequence":"additional","affiliation":[{"name":"Cold Spring Harbor Laboratory, Simons Center for Quantitative Biology, Cold Spring Harbor, NY 11724, U.S.A. julwang@cshl.edu"}]},{"given":"Saket","family":"Navlakha","sequence":"additional","affiliation":[{"name":"Cold Spring Harbor Laboratory, Simons Center for Quantitative Biology, Cold Spring Harbor, NY 11724, U.S.A. navlakha@cshl.edu"}]}],"member":"281","published-online":{"date-parts":[[2021,11,12]]},"reference":[{"key":"2021112221524685100_B1","article-title":"Theoretical analysis of auto rate-tuning by batch normalization.","author":"Arora","year":"2019","journal-title":"Proceedings of the 7th International Conference on Learning Representation"},{"key":"2021112221524685100_B2","first-page":"1168","article-title":"Normalization propagation: A parametric technique for removing internal covariate shift in deep networks.","author":"Arpit","year":"2016","journal-title":"Proceedings of the 33rd International Conference on Machine Learning"},{"issue":"3","key":"2021112221524685100_B3","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/j.neuron.2012.03.023","article-title":"Reduction of hippocampal hyperactivity improves cognition in amnestic mild cognitive impairment","volume":"74","author":"Bakker","year":"2012","journal-title":"Neuron"},{"issue":"1","key":"2021112221524685100_B4","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1523\/JNEUROSCI.02-01-00032.1982","article-title":"Theory for the development of neuron selectivity: orientation specificity and binocular interaction in visual cortex","volume":"2","author":"Bienenstock","year":"1982","journal-title":"J. Neurosci."},{"key":"2021112221524685100_B5","first-page":"7694","volume-title":"Advances in neural information processing systems","author":"Bjorck","year":"2018"},{"issue":"4","key":"2021112221524685100_B6","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1038\/nrn3687","article-title":"The log-dynamic brain: How skewed distributions affect network operations","volume":"15","author":"Buzsaki","year":"2014","journal-title":"Nat. Rev. Neurosci."},{"key":"2021112221524685100_B7","doi-asserted-by":"publisher","DOI":"10.1038\/133082a0","author":"Cannon","year":"1932","journal-title":"The wisdom of the body"},{"issue":"1","key":"2021112221524685100_B8","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1038\/nrn3136","article-title":"Normalization as a canonical neural computation","volume":"13","author":"Carandini","year":"2011","journal-title":"Nat. Rev. Neurosci."},{"key":"2021112221524685100_B9","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2015.00089","article-title":"Homeostatic role of heterosynaptic plasticity: models and experiments","volume":"9","author":"Chistiakova","year":"2015","journal-title":"Front. Comput. Neurosci."},{"key":"2021112221524685100_B10","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1146\/annurev.neuro.28.061604.135751","article-title":"Homeostatic control of neural activity: From phenomenology to molecular design","volume":"29","author":"Davis","year":"2006","journal-title":"Annu. Rev. Neurosci."},{"issue":"3","key":"2021112221524685100_B11","doi-asserted-by":"publisher","first-page":"718","DOI":"10.1016\/j.neuron.2013.09.044","article-title":"Homeostatic signaling and the stabilization of neural function","volume":"80","author":"Davis","year":"2013","journal-title":"Neuron"},{"key":"2021112221524685100_B12","first-page":"2071","volume-title":"Advances in neural information processing systems","author":"Desjardins","year":"2015"},{"issue":"1715","key":"2021112221524685100_B13","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2016.0413","article-title":"Integrating Hebbian and homeostatic plasticity: Introduction.","volume":"372","author":"Fox","year":"2017","journal-title":"Philos. Trans. R. Soc. Lond., B, Biol. Sci."},{"key":"2021112221524685100_B14","first-page":"658","volume-title":"Advances in neural information processing systems","author":"Ganguli","year":"2010"},{"issue":"10","key":"2021112221524685100_B15","doi-asserted-by":"crossref","first-page":"2103","DOI":"10.1162\/NECO_a_00638","article-title":"Efficient sensory encoding and Bayesian inference with heterogeneous neural populations","volume":"26","author":"Ganguli","year":"2014","journal-title":"Neural Comput."},{"issue":"18","key":"2021112221524685100_B16","doi-asserted-by":"publisher","first-page":"2901","DOI":"10.1016\/j.visres.2006.03.008","article-title":"Can the theory of \u201cwhitening\u201d explain the center-surround properties of retinal ganglion cell receptive fields?","volume":"46","author":"Graham","year":"2006","journal-title":"Vision Res."},{"issue":"2","key":"2021112221524685100_B17","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","article-title":"Neuroscience-inspired artificial intelligence","volume":"95","author":"Hassabis","year":"2017","journal-title":"Neuron"},{"issue":"6","key":"2021112221524685100_B18","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1093\/cercor\/bhh184","article-title":"Homeostatic synaptic plasticity can explain post-traumatic epileptogenesis in chronically isolated neocortex","volume":"15","author":"Houweling","year":"2005","journal-title":"Cereb. Cortex"},{"key":"2021112221524685100_B19","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms11353","article-title":"Temporal decorrelation by SK channels enables efficient neural coding and perception of natural stimuli","volume":"7","author":"Huang","year":"2016","journal-title":"Nat. Commun."},{"key":"2021112221524685100_B20","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift.","author":"Ioffe","year":"2015","journal-title":"Proceedings of the 32nd International Conference on Machine Learning"},{"issue":"28","key":"2021112221524685100_B21","doi-asserted-by":"publisher","first-page":"6778","DOI":"10.1523\/JNEUROSCI.0618-17.2017","article-title":"All for one but not one for all: Excitatory synaptic scaling and intrinsic excitability are coregulated by caMKIV, whereas inhibitory synaptic scaling is under independent control","volume":"37","author":"Joseph","year":"2017","journal-title":"Journal of Neuroscience"},{"issue":"1715","key":"2021112221524685100_B22","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2016.0158","article-title":"Integrating Hebbian and homeostatic plasticity: The current state of the field and future research directions.","volume":"372","author":"Keck","year":"2017","journal-title":"Philos. Trans. R. Soc. Lond., B, Biol. Sci."},{"key":"2021112221524685100_B23","first-page":"971","article-title":"Self-normalizing neural networks.","volume":"30","author":"Klambauer","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"2021112221524685100_B24","first-page":"806","article-title":"Exponential convergence rates for batch normalization: The power of length-direction decoupling in non-convex optimization.","author":"Kohler","year":"2019","journal-title":"Proceedings of Machine Learning Research"},{"key":"2021112221524685100_B25","author":"Krishnan","year":"2019","journal-title":"Biologically inspired sleep algorithm for artificial neural networks."},{"key":"2021112221524685100_B26","article-title":"Regularization for deep learning: A taxonomy.","author":"Kukacka","year":"2017","journal-title":"CoRR"},{"key":"2021112221524685100_B27","author":"Lang","year":"1990","journal-title":"Dimensionality reduction and prior knowledge in e-set recognition"},{"issue":"9\u201310","key":"2021112221524685100_B28","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1515\/znc-1981-9-1040","article-title":"A simple coding procedure enhances a neuron's information capacity","volume":"36","author":"Laughlin","year":"1981","journal-title":"Zeitschrift f\u00fcr Naturforschung c"},{"issue":"5641","key":"2021112221524685100_B29","doi-asserted-by":"publisher","first-page":"1870","DOI":"10.1126\/science.1089662","article-title":"Communication in neuronal networks","volume":"301","author":"Laughlin","year":"2003","journal-title":"Science"},{"issue":"11","key":"2021112221524685100_B30","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun","year":"1998","journal-title":"Proceedings of the IEEE"},{"key":"2021112221524685100_B31","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1007\/978-3-642-35289-8_3","volume-title":"Neural networks: Tricks of the trade","author":"LeCun","year":"1998"},{"key":"2021112221524685100_B32","author":"Ba","year":"2016","journal-title":"Layer normalization"},{"issue":"29","key":"2021112221524685100_B33","doi-asserted-by":"crossref","first-page":"12084","DOI":"10.1073\/pnas.1305857110","article-title":"Transformation of odor selectivity from projection neurons to single mushroom body neurons mapped with dual-color calcium imaging","volume":"110","author":"Li","year":"2013","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"2021112221524685100_B34","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1038\/s41583-020-0277-3","article-title":"Backpropagation and the brain","volume":"21","author":"Lillicrap","year":"2020","journal-title":"Nature Reviews Neuroscience"},{"key":"2021112221524685100_B35","author":"Luo","year":"2018","journal-title":"Towards understanding regularization in batch normalization."},{"key":"2021112221524685100_B36","author":"Lynch","year":"1996","journal-title":"Distributed algorithms"},{"issue":"2","key":"2021112221524685100_B37","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1016\/j.conb.2009.05.012","article-title":"Network homeostasis: A matter of coordination","volume":"19","author":"Maffei","year":"2009","journal-title":"Curr. Opin. Neurobiol."},{"issue":"5","key":"2021112221524685100_B38","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1016\/s0092-8674(00)80581-4","article-title":"Combinatorial receptor codes for odors","volume":"96","author":"Malnic","year":"1999","journal-title":"Cell"},{"issue":"12","key":"2021112221524685100_B39","doi-asserted-by":"crossref","first-page":"1690","DOI":"10.1038\/nn1556","article-title":"Independence of luminance and contrast in natural scenes and in the early visual system","volume":"8","author":"Mante","year":"2005","journal-title":"Nat. Neurosci."},{"issue":"7","key":"2021112221524685100_B40","doi-asserted-by":"publisher","first-page":"563","DOI":"10.1038\/nrn1949","article-title":"Variability, compensation and homeostasis in neuron and network function","volume":"7","author":"Marder","year":"2006","journal-title":"Nat. Rev. Neurosci."},{"issue":"4","key":"2021112221524685100_B41","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1016\/s0896-6273(01)00500-1","article-title":"Inactivity produces increases in neurotransmitter release and synapse size","volume":"32","author":"Murthy","year":"2001","journal-title":"Neuron"},{"key":"2021112221524685100_B42","author":"Neyshabur","year":"2017","journal-title":"Geometry of optimization and implicit regularization in deep learning"},{"issue":"2","key":"2021112221524685100_B43","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.neuron.2010.04.009","article-title":"Divisive normalization in olfactory population codes","volume":"66","author":"Olsen","year":"2010","journal-title":"Neuron"},{"issue":"4","key":"2021112221524685100_B44","doi-asserted-by":"publisher","first-page":"481","DOI":"10.1016\/j.conb.2004.07.007","article-title":"Sparse coding of sensory inputs","volume":"14","author":"Olshausen","year":"2004","journal-title":"Current Opinion in Neurobiology"},{"issue":"4","key":"2021112221524685100_B45","doi-asserted-by":"publisher","first-page":"628","DOI":"10.1038\/nn.3064","article-title":"Decorrelation and efficient coding by retinal ganglion cells","volume":"15","author":"Pitkow","year":"2012","journal-title":"Nat. Neurosci."},{"issue":"1","key":"2021112221524685100_B46","doi-asserted-by":"crossref","DOI":"10.1038\/s41467-020-14663-9","article-title":"Complexity control by gradient descent in deep networks","volume":"11","author":"Poggio","year":"2020","journal-title":"Nat. Commun."},{"issue":"3","key":"2021112221524685100_B47","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1016\/j.neuron.2010.04.028","article-title":"Unraveling mechanisms of homeostatic synaptic plasticity","volume":"66","author":"Pozo","year":"2010","journal-title":"Neuron"},{"issue":"7","key":"2021112221524685100_B48","doi-asserted-by":"publisher","first-page":"942","DOI":"10.1038\/nn.3431","article-title":"Temporal whitening by power-law adaptation in neocortical neurons","volume":"16","author":"Pozzorini","year":"2013","journal-title":"Nat. Neurosci."},{"issue":"4","key":"2021112221524685100_B49","doi-asserted-by":"publisher","first-page":"602","DOI":"10.1016\/s0896-6273(02)00829-2","article-title":"A new mechanism for neuronal gain control (or how the gain in brains has mainly been explained)","volume":"35","author":"Priebe","year":"2002","journal-title":"Neuron"},{"issue":"12","key":"2021112221524685100_B50","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1038\/nn1352","article-title":"Similar network activity from disparate circuit parameters","volume":"7","author":"Prinz","year":"2004","journal-title":"Nat. Neurosci."},{"issue":"8","key":"2021112221524685100_B51","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.tins.2008.05.005","article-title":"Two opposing plasticity mechanisms pulling a single synapse","volume":"31","author":"Rabinowitch","year":"2008","journal-title":"Trends Neurosci."},{"issue":"6","key":"2021112221524685100_B52","doi-asserted-by":"publisher","first-page":"1178","DOI":"10.1016\/j.neuron.2011.04.030","article-title":"Contrast gain control in auditory cortex","volume":"70","author":"Rabinowitz","year":"2011","journal-title":"Neuron"},{"key":"2021112221524685100_B53","article-title":"Deep learning made easier by linear transformations in perceptrons.","author":"Raiko","year":"2012","journal-title":"Proceedings of the Fifteenth International Conference on Artificial Intelligence and Statistics"},{"key":"2021112221524685100_B54","article-title":"Normalizing the normalizers: Comparing and extending network normalization schemes.","author":"Ren","year":"2017","journal-title":"Proceedings of the 5th International Conference on Learning Representations"},{"key":"2021112221524685100_B55","author":"Rodieck","year":"1998","journal-title":"The first steps in seeing"},{"issue":"6931","key":"2021112221524685100_B56","doi-asserted-by":"publisher","first-page":"518","DOI":"10.1038\/nature01530","article-title":"Conservation of total synaptic weight through balanced synaptic depression and potentiation","volume":"422","author":"Royer","year":"2003","journal-title":"Nature"},{"key":"2021112221524685100_B57","first-page":"901","volume-title":"Advances in neural information processing systems","author":"Salimans","year":"2016"},{"key":"2021112221524685100_B58","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.conb.2019.01.008","article-title":"Normalization and pooling in hierarchical models of natural images","volume":"55","author":"Sanchez-Giraldo","year":"2019","journal-title":"Curr. Opin. Neurobiol."},{"key":"2021112221524685100_B59","first-page":"2483","article-title":"How does batch normalization help optimization?","volume":"31","author":"Santurkar","year":"2018","journal-title":"Advances in neural information processing systems"},{"issue":"8","key":"2021112221524685100_B60","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1038\/90526","article-title":"Natural signal statistics and sensory gain control","volume":"4","author":"Schwartz","year":"2001","journal-title":"Nat. Neurosci."},{"issue":"7","key":"2021112221524685100_B61","doi-asserted-by":"crossref","first-page":"R421","DOI":"10.1016\/S0960-9822(06)00207-7","article-title":"Retinal physiology: Adapting to the changing scene","volume":"7","author":"Shapley","year":"1997","journal-title":"Curr. Biol."},{"key":"2021112221524685100_B62","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.04378","article-title":"Interplay between population firing stability and single neuron dynamics in hippocampal networks.","volume":"4","author":"Slomowitz","year":"2015","journal-title":"eLife"},{"issue":"1","key":"2021112221524685100_B63","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"issue":"30","key":"2021112221524685100_B64","doi-asserted-by":"crossref","first-page":"9460","DOI":"10.1073\/pnas.1510103112","article-title":"What the fly's nose tells the fly's brain","volume":"112","author":"Stevens","year":"2015","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"issue":"24","key":"2021112221524685100_B65","doi-asserted-by":"crossref","first-page":"6737","DOI":"10.1073\/pnas.1606339113","article-title":"A statistical property of fly odor responses is conserved across odors","volume":"113","author":"Stevens","year":"2016","journal-title":"Proc. Natl. Acad. Sci. U.S.A."},{"key":"2021112221524685100_B66","doi-asserted-by":"crossref","DOI":"10.1155\/2012\/415250","article-title":"Time to be SHY? Some comments on sleep and synaptic homeostasis","volume":"2012","author":"Tononi","year":"2012","journal-title":"Neural Plast."},{"key":"2021112221524685100_B67","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.37836","article-title":"Competition for synaptic building blocks shapes synaptic plasticity.","volume":"7","author":"Triesch","year":"2018","journal-title":"eLife"},{"issue":"3","key":"2021112221524685100_B68","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1016\/j.cell.2008.10.008","article-title":"The self-tuning neuron: Synaptic scaling of excitatory synapses","volume":"135","author":"Turrigiano","year":"2008","journal-title":"Cell"},{"key":"2021112221524685100_B69","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1146\/annurev-neuro-060909-153238","article-title":"Too many cooks? Intrinsic and synaptic homeostatic mechanisms in cortical circuit refinement","volume":"34","author":"Turrigiano","year":"2011","journal-title":"Annu. Rev. Neurosci."},{"issue":"1","key":"2021112221524685100_B70","doi-asserted-by":"publisher","DOI":"10.1101\/cshperspect.a005736","article-title":"Homeostatic synaptic plasticity: Local and global mechanisms for stabilizing neuronal function","volume":"4","author":"Turrigiano","year":"2012","journal-title":"Cold Spring Harb. Perspect. Biol."},{"issue":"1715","key":"2021112221524685100_B71","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2016.0258","article-title":"The dialectic of Hebb and homeostasis.","volume":"372","author":"Turrigiano","year":"2017","journal-title":"Philos. Trans. R. Soc. Lond., B, Biol. Sci."},{"issue":"2","key":"2021112221524685100_B72","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1038\/nrn1327","article-title":"Homeostatic plasticity in the developing nervous system","volume":"5","author":"Turrigiano","year":"2004","journal-title":"Nat. Rev. Neurosci."},{"key":"2021112221524685100_B73","author":"Ulyanov","year":"2016","journal-title":"Instance normalization: The missing ingredient for fast stylization"},{"key":"2021112221524685100_B74","first-page":"2168","volume-title":"Advances in neural information processing systems","author":"Wang","year":"2012"},{"issue":"12","key":"2021112221524685100_B75","doi-asserted-by":"publisher","first-page":"2656","DOI":"10.1162\/NECO_a_00900","article-title":"Efficient neural codes that minimize Lp reconstruction error","volume":"28","author":"Wang","year":"2016","journal-title":"Neural Comput."},{"issue":"3","key":"2021112221524685100_B76","doi-asserted-by":"publisher","first-page":"433","DOI":"10.1038\/s41593-019-0576-z","article-title":"Whitening of odor representations by the wiring diagram of the olfactory bulb","volume":"23","author":"Wanner","year":"2020","journal-title":"Nat. Neurosci."},{"key":"2021112221524685100_B77","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1146\/annurev-vision-091718-014818","article-title":"Coding principles in adaptation","volume":"5","author":"Weber","year":"2019","journal-title":"Annu. Rev. Vis. Sci."},{"issue":"3","key":"2021112221524685100_B78","doi-asserted-by":"publisher","first-page":"671","DOI":"10.1162\/089976698300017700","article-title":"Constrained optimization for neural map formation: A unifying framework for weight growth and normalization","volume":"10","author":"Wiskott","year":"1998","journal-title":"Neural Computation"},{"key":"2021112221524685100_B79","doi-asserted-by":"publisher","DOI":"10.3389\/fncel.2013.00223","article-title":"Emerging links between homeostatic synap tic plasticity and neurological disease","volume":"7","author":"Wondolowski","year":"2013","journal-title":"Front. Cell. Neurosci."},{"key":"2021112221524685100_B80","author":"Wu","year":"2019","journal-title":"Implicit regularization of normalization methods"},{"key":"2021112221524685100_B81","article-title":"Group normalization.","author":"Wu","year":"2018","journal-title":"Proceedings of the European Conference on Computer Vision"},{"issue":"1","key":"2021112221524685100_B82","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1016\/j.neuroimage.2006.11.047","article-title":"Role of hyperactive cerebellum and motor cortex in Parkinson's disease","volume":"35","author":"Yu","year":"2007","journal-title":"NeuroImage"},{"issue":"1715","key":"2021112221524685100_B83","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2016.0259","article-title":"Hebbian plasticity requires compensatory processes on multiple timescales.","volume":"372","author":"Zenke","year":"2017","journal-title":"Philos. Trans. R. Soc. Lond., B, Biol. Sci."},{"issue":"11","key":"2021112221524685100_B84","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1038\/nrn1248","article-title":"The other side of the engram: Experience-driven changes in neuronal intrinsic excitability","volume":"4","author":"Zhang","year":"2003","journal-title":"Nat. Rev. Neurosci."},{"issue":"3","key":"2021112221524685100_B85","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1038\/nn.3329","article-title":"Long-term dynamics of CA1 hippocampal place codes","volume":"16","author":"Ziv","year":"2013","journal-title":"Nat. Neurosci."},{"issue":"2","key":"2021112221524685100_B86","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1111\/j.1467-9868.2005.00503.x","article-title":"Regularization and variable selection via the elastic net","volume":"67","author":"Zou","year":"2005","journal-title":"Journal of the Royal Statistical Society. Series B (Statistical Methodology)"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/33\/12\/3179\/1971993\/neco_a_01439.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/33\/12\/3179\/1971993\/neco_a_01439.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,11,22]],"date-time":"2021-11-22T16:53:47Z","timestamp":1637600027000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/33\/12\/3179\/107074\/A-Correspondence-Between-Normalization-Strategies"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,12]]},"references-count":86,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,11,12]]},"published-print":{"date-parts":[[2021,11,12]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01439","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/2020.07.17.197640","asserted-by":"object"}]},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,12]]},"published":{"date-parts":[[2021,11,12]]}}}