{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T06:30:25Z","timestamp":1768285825031,"version":"3.49.0"},"reference-count":89,"publisher":"MIT Press","issue":"12","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,11,19]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The sparse coding model posits that the visual system has evolved to efficiently code natural stimuli using a sparse set of features from an overcomplete dictionary. The original sparse coding model suffered from two key limitations; however: (1) computing the neural response to an image patch required minimizing a nonlinear objective function via recurrent dynamics and (2) fitting relied on approximate inference methods that ignored uncertainty. Although subsequent work has developed several methods to overcome these obstacles, we propose a novel solution inspired by the variational autoencoder (VAE) framework. We introduce the sparse coding variational autoencoder (SVAE), which augments the sparse coding model with a probabilistic recognition model parameterized by a deep neural network. This recognition model provides a neurally plausible feedforward implementation for the mapping from image patches to neural activities and enables a principled method for fitting the sparse coding model to data via maximization of the evidence lower bound (ELBO). The SVAE differs from standard VAEs in three key respects: the latent representation is overcomplete (there are more latent dimensions than image pixels), the prior is sparse or heavy-tailed instead of gaussian, and the decoder network is a linear projection instead of a deep network. We fit the SVAE to natural image data under different assumed prior distributions and show that it obtains higher test performance than previous fitting methods. Finally, we examine the response properties of the recognition network and show that it captures important nonlinear properties of neurons in the early visual pathway.<\/jats:p>","DOI":"10.1162\/neco_a_01715","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T16:22:57Z","timestamp":1728490977000},"page":"2571-2601","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":6,"title":["Sparse-Coding Variational Autoencoders"],"prefix":"10.1162","volume":"36","author":[{"given":"Victor","family":"Geadah","sequence":"first","affiliation":[{"name":"Program in Applied and Computational Mathematics, Princeton University, Princeton, NJ 08544, U.S.A. victor.geadah@princeton.edu"}]},{"given":"Gabriel","family":"Barello","sequence":"additional","affiliation":[{"name":"Institute of Neuroscience, University of Oregon, Eugene, OR 97403, U.S.A. gabrielbarello@gmail.com"}]},{"given":"Daniel","family":"Greenidge","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Princeton University, Princeton, NJ 08544, U.S.A. daniel@danielgreenidge.com"}]},{"given":"Adam S.","family":"Charles","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, Department Center for Imaging Science, and Department Kavli Neuroscience Discovery Institute, Baltimore, MD 21218, U.S.A. adamsc@jhu.edu"}]},{"given":"Jonathan W.","family":"Pillow","sequence":"additional","affiliation":[{"name":"Princeton Neuroscience Institute, Princeton University, Princeton, NJ 08544, U.S.A. pillow@princeton.edu"}]}],"member":"281","published-online":{"date-parts":[[2024,11,19]]},"reference":[{"key":"2024111519195583300_bib1","author":"Aitchison","year":"2018","journal-title":"Sampling-based probabilistic inference emerges from learning in neural circuits with a cost on reliability"},{"issue":"5","key":"2024111519195583300_bib2","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1888","article-title":"Neural correlations, population coding and computation","volume":"7","author":"Averbeck","year":"2006","journal-title":"Nature Reviews Neuroscience"},{"issue":"1","key":"2024111519195583300_bib3","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1137\/080716542","article-title":"A fast iterative shrinkage-thresholding algorithm for linear inverse problems","volume":"2","author":"Beck","year":"2009","journal-title":"SIAM Journal on Imaging Sciences"},{"key":"2024111519195583300_bib4","author":"Bengio","year":"2015","journal-title":"Towards biologically plausible deep learning"},{"key":"2024111519195583300_bib5","first-page":"89","article-title":"On sparsity and overcompleteness in image models","volume-title":"Advances in neural information processing systems","author":"Berkes","year":"2008"},{"issue":"6","key":"2024111519195583300_bib6","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1167\/5.6.9","article-title":"Slow feature analysis yields a rich repertoire of complex cell properties","volume":"5","author":"Berkes","year":"2005","journal-title":"Journal of Vision"},{"key":"2024111519195583300_bib7","volume-title":"Neural networks for pattern recognition","author":"Bishop","year":"2005"},{"key":"2024111519195583300_bib8","author":"Blei","year":"2016","journal-title":"Variational inference: A review for statisticians"},{"issue":"2","key":"2024111519195583300_bib9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1001080","article-title":"Spike-based population coding and working memory","volume":"7","author":"Boerlin","year":"2011","journal-title":"PLOS Computational Biology"},{"issue":"16","key":"2024111519195583300_bib10","doi-asserted-by":"publisher","first-page":"4293","DOI":"10.1109\/TSP.2017.2708040","article-title":"Amp-inspired deep networks for sparse linear inverse problems","volume":"65","author":"Borgerding","year":"2017","journal-title":"IEEE Transactions on Signal Processing"},{"key":"2024111519195583300_bib11","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511804441","volume-title":"Convex optimization","author":"Boyd","year":"2004"},{"key":"2024111519195583300_bib12","first-page":"209","article-title":"Learning transformational invariants from natural movies","volume-title":"Advances in neural information processing systems","author":"Cadieu","year":"2009"},{"issue":"12","key":"2024111519195583300_bib13","doi-asserted-by":"publisher","first-page":"3317","DOI":"10.1162\/NECO_a_00372","article-title":"A common network architecture efficiently implements a variety of sparsity-based inference problems","volume":"24","author":"Charles","year":"2012","journal-title":"Neural Computation"},{"issue":"5","key":"2024111519195583300_bib14","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1109\/JSTSP.2011.2149497","article-title":"Learning sparse codes for hyperspectral imagery","volume":"5","author":"Charles","year":"2011","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"4","key":"2024111519195583300_bib15","doi-asserted-by":"publisher","first-page":"1012","DOI":"10.1162\/neco_a_01062","article-title":"Dethroning the Fano factor: A flexible, model-based approach to partitioning neural variability","volume":"30","author":"Charles","year":"2018","journal-title":"Neural Computation"},{"key":"2024111519195583300_bib16","article-title":"Isolating sources of disentanglement in variational autoencoders","volume-title":"Advances in neural information processing systems","author":"Chen","year":"2018"},{"issue":"3","key":"2024111519195583300_bib17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002405","article-title":"Cortical surround interactions and perceptual salience via natural scene statistics","volume":"8","author":"Coen-Cagli","year":"2012","journal-title":"PLOS Computational Biology"},{"issue":"7","key":"2024111519195583300_bib18","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1038\/nn.2842","article-title":"Measuring and interpreting neuronal correlations","volume":"14","author":"Cohen","year":"2011","journal-title":"Nature Neuroscience"},{"issue":"1","key":"2024111519195583300_bib19","first-page":"1573","article-title":"Connections with robust PCA and the role of emergent sparsity in variational autoencoder models","volume":"19","author":"Dai","year":"2018","journal-title":"Journal of Machine Learning Research"},{"issue":"11","key":"2024111519195583300_bib20","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1002\/cpa.20042","article-title":"An iterative thresholding algorithm for linear inverse problems with a sparsity constraint","volume":"57","author":"Daubechies","year":"2004","journal-title":"Communications on Pure and Applied Mathematics"},{"key":"2024111519195583300_bib21","article-title":"Adaptation and unsupervised learning","volume-title":"Advances in neural information processing systems","author":"Dayan","year":"2003"},{"key":"2024111519195583300_bib22","author":"Doersch","year":"2016","journal-title":"Tutorial on variational autoencoders."},{"issue":"1","key":"2024111519195583300_bib23","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1162\/neco.1989.1.1.133","article-title":"Product units: A computationally powerful and biologically plausible extension to backpropagation networks","volume":"1","author":"Durbin","year":"1989","journal-title":"Neural Computation"},{"issue":"40","key":"2024111519195583300_bib24","doi-asserted-by":"publisher","first-page":"14272","DOI":"10.1523\/JNEUROSCI.2539-11.2011","article-title":"The effect of noise correlations in populations of diversely tuned neurons","volume":"31","author":"Ecker","year":"2011","journal-title":"Journal of Neuroscience"},{"issue":"3","key":"2024111519195583300_bib25","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.tics.2010.01.003","article-title":"Statistically optimal perception and learning: From behavior to neural representations","volume":"14","author":"Fiser","year":"2010","journal-title":"Trends in Cognnitive Sciences"},{"issue":"1","key":"2024111519195583300_bib26","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1113\/ jphysiol.1985.sp015776","article-title":"Spatial and temporal frequency selectivity of neurones in visual cortical areas V1 and V2 of the macaque monkey","volume":"365","author":"Foster","year":"1985","journal-title":"Journal of Physiology"},{"issue":"26","key":"2024111519195583300_bib27","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1049\/ji-3-2.1946.0074","article-title":"Theory of communication. Part 1: The analysis of information","volume":"93","author":"Gabor","year":"1946","journal-title":"Journal of the Institution of Electrical Engineers\u2014Part III: Radio and Communication Engineering"},{"key":"2024111519195583300_bib28","first-page":"505","article-title":"Learning horizontal connections in a sparse coding model of natural images","volume-title":"Advances in neural information processing systems","author":"Garrigues","year":"2008"},{"key":"2024111519195583300_bib29","first-page":"676","article-title":"Group sparse coding with a Laplacian scale mixture prior","volume-title":"Advances in neural information processing systems","author":"Garrigues","year":"2010"},{"issue":"11","key":"2024111519195583300_bib30","doi-asserted-by":"publisher","first-page":"2517","DOI":"10.1162\/089976601753196003","article-title":"A variational method for learning sparse and overcomplete representations","volume":"13","author":"Girolami","year":"2001","journal-title":"Neural Computation"},{"key":"2024111519195583300_bib31","doi-asserted-by":"publisher","DOI":"10.1038\/nn.3711","article-title":"Partitioning neuronal variability","volume":"17","author":"Goris","year":"2014","journal-title":"Nature Neuroscience"},{"key":"2024111519195583300_bib32","first-page":"399","article-title":"Learning fast approximations of sparse coding","volume-title":"Proceedings of the 27th International Conference on Machine Learning","author":"Gregor","year":"2010"},{"issue":"3","key":"2024111519195583300_bib33","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1016\/j.neuron.2012.08.029","article-title":"Correlated variability in laminar cortical circuits","volume":"76","author":"Hansen","year":"2012","journal-title":"Neuron"},{"key":"2024111519195583300_bib34","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1113\/jphysiol.1962.sp006837","article-title":"Receptive fields, binocular interaction and functional architecture in the cat\u2019s visual cortex","volume":"160","author":"Hubel","year":"1962","journal-title":"Journal of Physiology (London)"},{"key":"2024111519195583300_bib35","author":"Jang","year":"2016","journal-title":"Categorical reparameterization with Gumbel-Softmax"},{"issue":"3","key":"2024111519195583300_bib36","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1088\/0954-898X_14_3_306","article-title":"Learning higher-order structures in natural images","volume":"14","author":"Karklin","year":"2003","journal-title":"Network"},{"issue":"2","key":"2024111519195583300_bib37","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1162\/0899766053011474","article-title":"A hierarchical Bayesian model for learning nonlinear statistical regularities in nonstationary natural signals","volume":"17","author":"Karklin","year":"2005","journal-title":"Neural Computation"},{"issue":"7225","key":"2024111519195583300_bib38","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1038\/nature07481","article-title":"Emergence of complex cell properties by learning to generalize in natural scenes","volume":"457","author":"Karklin","year":"2009","journal-title":"Nature"},{"key":"2024111519195583300_bib39","article-title":"Topographic VAEs learn equivariant capsules","author":"Keller","year":"2021","journal-title":"Advances in neural information processing systems."},{"key":"2024111519195583300_bib40","first-page":"2207","article-title":"Variational autoencoders and nonlinear ICA: A unifying framework","volume-title":"Proceedings of the International Conference on Artificial Intelligence and Statistics","author":"Khemakhem","year":"2020"},{"key":"2024111519195583300_bib41","author":"Kingma","year":"2014","journal-title":"Adam: A method for stochastic optimization"},{"key":"2024111519195583300_bib42","author":"Kingma","year":"2014","journal-title":"Auto-encoding variational Bayes."},{"issue":"12","key":"2024111519195583300_bib43","doi-asserted-by":"publisher","first-page":"712","DOI":"10.1016\/j.tins.2004.10.007","article-title":"The Bayesian brain: The role of uncertainty in neural coding and computation","volume":"27","author":"Knill","year":"2004","journal-title":"Trends in Neurosciences"},{"key":"2024111519195583300_bib44","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511984037","volume-title":"Perception as Bayesian inference","author":"Knill","year":"1996"},{"key":"2024111519195583300_bib45","first-page":"801","article-title":"Efficient sparse coding algorithms","volume-title":"Advances in neural information processing systems","author":"Lee","year":"2007"},{"issue":"7","key":"2024111519195583300_bib46","doi-asserted-by":"publisher","first-page":"1587","DOI":"10.1364\/JOSAA.16.001587","article-title":"Probabilistic framework for the adaptation and comparison of image codes","volume":"16","author":"Lewicki","year":"1999","journal-title":"JOSA A"},{"key":"2024111519195583300_bib47","author":"Maddison","year":"2016","journal-title":"The concrete distribution: A continuous relaxation of discrete random variables"},{"key":"2024111519195583300_bib48","author":"Maddison","year":"2016","journal-title":"The concrete distribution: A continuous relaxation of discrete random variables"},{"key":"2024111519195583300_bib49","author":"Makhzani","year":"2013","journal-title":"K-sparse autoencoders"},{"key":"2024111519195583300_bib50","first-page":"416","article-title":"A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics","volume-title":"Proceedings of the International Conference on Computer Vision","author":"Martin","year":"2001"},{"key":"2024111519195583300_bib51","first-page":"1500","article-title":"Structured sparsity in structured prediction","volume-title":"Proceedings of the Conference on Empirical Methods in Natural Language Processing","author":"Martins","year":"2011"},{"key":"2024111519195583300_bib52","article-title":"Neural variational inference and learning in belief networks","volume-title":"Proceedings of the Annual International Conference on Machine Learning.","author":"Mnih","year":"2014"},{"issue":"30","key":"2024111519195583300_bib53","doi-asserted-by":"publisher","first-page":"12491","DOI":"10.1073\/pnas.1101430108","article-title":"Bayesian sampling in visual perception","volume":"108","author":"Moreno-Bote","year":"2011","journal-title":"Proceedings of the National Academy of Sciences USA"},{"key":"2024111519195583300_bib54","article-title":"Tutorial on Gabor filters","volume":"40","author":"Movellan","year":"2002","journal-title":"Open source document"},{"issue":"2","key":"2024111519195583300_bib55","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1023\/A:1008923215028","article-title":"Annealed importance sampling","volume":"11","author":"Neal","year":"2001","journal-title":"Statistics and Computing"},{"key":"2024111519195583300_bib56","doi-asserted-by":"publisher","DOI":"10.1201\/b10905","article-title":"MCMC using Hamiltonian dynamics","volume-title":"Handbook of Markov chain Monte Carlo.","author":"Neal","year":"2011"},{"key":"2024111519195583300_bib57","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1007\/978-94-011-5014-9_12","article-title":"A view of the EM algorithm that justifies incremental, sparse, and other variants","volume-title":"Learning in graphical models","author":"Neal","year":"1998"},{"key":"2024111519195583300_bib58","volume-title":"Learning linear, sparse, factorial codes.","author":"Olshausen","year":"1996"},{"key":"2024111519195583300_bib59","doi-asserted-by":"publisher","DOI":"10.1038\/381607a0","article-title":"Emergence of simple-cell receptive field properties by learning a sparse code for natural images","volume":"381","author":"Olshausen","year":"1996","journal-title":"Nature"},{"issue":"2","key":"2024111519195583300_bib60","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1088\/0954-898X\/7\/2\/014","article-title":"Natural image statistics and efficient coding","volume":"7","author":"Olshausen","year":"1996","journal-title":"Network"},{"issue":"23","key":"2024111519195583300_bib61","doi-asserted-by":"publisher","first-page":"3311","DOI":"10.1016\/S0042-6989(97)00169-7","article-title":"Sparse coding with an overcomplete basis set: A strategy employed by V1?","volume":"37","author":"Olshausen","year":"1997","journal-title":"Vision Research"},{"key":"2024111519195583300_bib62","first-page":"841","article-title":"Learning sparse codes with a mixture- of-gaussians prior","volume-title":"Advances in neural information processing systems","author":"Olshausen","year":"2000"},{"issue":"2","key":"2024111519195583300_bib63","doi-asserted-by":"crossref","first-page":"530","DOI":"10.1016\/j.neuron.2016.09.038","article-title":"Neural variability and sampling-based probabilistic representations in the visual cortex","volume":"92","author":"Orb\u00e1n","year":"2016","journal-title":"Neuron"},{"key":"2024111519195583300_bib64","author":"Paszke","year":"2017","journal-title":"Automatic differentiation in PyTorch"},{"key":"2024111519195583300_bib65","volume-title":"Probabilistic reasoning in intelligent systems: Networks of plausible inference","author":"Pearl","year":"1988"},{"key":"2024111519195583300_bib66","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","volume-title":"Proceedings of the 31st International Conference on Machine Learning","author":"Rezende","year":"2014"},{"issue":"1","key":"2024111519195583300_bib67","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1152\/jn.2002.88.1.455","article-title":"Spatial structure and symmetry of simple-cell receptive fields in macaque primary visual cortex","volume":"88","author":"Ringach","year":"2002","journal-title":"Journal of Neurophysiology"},{"key":"2024111519195583300_bib68","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1207\/s15516709cog2802_2","article-title":"Reverse correlation in neurophysiology","volume":"28","author":"Ringach","year":"2004","journal-title":"Cognitive Science"},{"issue":"10","key":"2024111519195583300_bib69","doi-asserted-by":"publisher","first-page":"2526","DOI":"10.1162\/neco.2008.03-07-486","article-title":"Sparse coding via thresholding and local competition in neural circuits","volume":"20","author":"Rozell","year":"2008","journal-title":"Neural Computation"},{"key":"2024111519195583300_bib70","author":"Salimans","year":"2016","journal-title":"A structured variational auto-encoder for learning deep hierarchies of sparse features."},{"issue":"8","key":"2024111519195583300_bib71","doi-asserted-by":"publisher","DOI":"10.1038\/11197","article-title":"Contrast\u2019s effect on spatial summation by macaque V1 neurons","volume":"2","author":"Sceniak","year":"1999","journal-title":"Nature Neuroscience"},{"issue":"28","key":"2024111519195583300_bib72","doi-asserted-by":"publisher","first-page":"10112","DOI":"10.1523\/JNEUROSCI.4951-14.2015","article-title":"Constructing precisely computing networks with biophysical spiking neurons","volume":"35","author":"Schwemmer","year":"2015","journal-title":"Journal of Neuroscience"},{"issue":"April","key":"2024111519195583300_bib73","first-page":"759","article-title":"Bayesian inference and optimal design for the sparse linear model","volume":"9","author":"Seeger","year":"2008","journal-title":"Journal of Machine Learning Research"},{"issue":"5","key":"2024111519195583300_bib74","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065714400012","article-title":"Optimal sparse approximation with integrate and fire neurons","volume":"24","author":"Shapero","year":"2014","journal-title":"International Journal of Neural Systems"},{"issue":"1","key":"2024111519195583300_bib75","doi-asserted-by":"publisher","first-page":"1193","DOI":"10.1146\/annurev.neuro.24.1.1193","article-title":"Natural image statistics and neural representation","volume":"24","author":"Simoncelli","year":"2001","journal-title":"Annual Review of Neuroscience"},{"issue":"7079","key":"2024111519195583300_bib76","doi-asserted-by":"publisher","DOI":"10.1038\/nature04485","article-title":"Efficient auditory coding","volume":"439","author":"Smith","year":"2006","journal-title":"Nature"},{"key":"2024111519195583300_bib77","doi-asserted-by":"publisher","first-page":"33353","DOI":"10.1109\/ACCESS.2018.2848210","article-title":"Learning sparse representation with variational auto-encoder for anomaly detection","volume":"6","author":"Sun","year":"2018","journal-title":"IEEE Access"},{"key":"2024111519195583300_bib78","first-page":"1124","article-title":"Training sparse natural image models with a fast Gibbs sampler of an extended state space","volume-title":"Advances in neural information processing systems","author":"Theis","year":"2012"},{"issue":"5","key":"2024111519195583300_bib79","doi-asserted-by":"crossref","first-page":"941","DOI":"10.1109\/JSTSP.2011.2158063","article-title":"Learning sparse representations of depth","volume":"5","author":"T\u01d2sic","year":"2011","journal-title":"IEEE Journal of Selected Topics in Signal Processing"},{"issue":"15","key":"2024111519195583300_bib80","doi-asserted-by":"publisher","first-page":"5908","DOI":"10.1523\/JNEUROSCI.18-15-05908.1998","article-title":"Contrast-invariant orientation tuning in cat visual cortex: Thalamocortical input tuning and correlation-based intracortical connectivity","volume":"18","author":"Troyer","year":"1998","journal-title":"Journal of Neuroscience"},{"key":"2024111519195583300_bib81","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1017\/CBO9780511984679.006","article-title":"Two problems with variational expectation maximisation for time-series models","volume-title":"Bayesian time series models","author":"Turner","year":"2011"},{"key":"2024111519195583300_bib82","article-title":"Neural discrete representation learning","volume-title":"Advances in neural information processing systems","author":"Van Den Oord","year":"2017"},{"key":"2024111519195583300_bib83","author":"Velychko","year":"2023","journal-title":"Learning sparse codes with entropy-based ELBOs."},{"key":"2024111519195583300_bib84","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1038\/nn0602-858","article-title":"Motion illusions as optimal percepts","volume":"5","author":"Weiss","year":"2002","journal-title":"Nature Neuroscience"},{"key":"2024111519195583300_bib85","author":"Wu","year":"2016","journal-title":"On the quantitative analysis of decoder-based generative models."},{"key":"2024111519195583300_bib86","first-page":"40","article-title":"Structured recognition for generative models with explaining away","volume-title":"Advances in neural information processing systems","author":"Yu","year":"2022"},{"issue":"8","key":"2024111519195583300_bib87","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1003191","article-title":"Visual nonclassical receptive field effects emerge from sparse coding in a dynamical system","volume":"9","author":"Zhu","year":"2013","journal-title":"PLOS Computational Biology"},{"issue":"21","key":"2024111519195583300_bib88","doi-asserted-by":"publisher","first-page":"5270","DOI":"10.1109\/TSP.2013.2273196","article-title":"Dynamic compressive sensing of time-varying signals via approximate message passing","volume":"61","author":"Ziniel","year":"2013","journal-title":"IEEE Transactions on Signal Processing"},{"issue":"10","key":"2024111519195583300_bib89","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1002250","article-title":"A sparse coding model with synaptically local plasticity and spiking neurons can account for the diverse shapes of V1 simple cell receptive fields","volume":"7","author":"Zylberberg","year":"2011","journal-title":"PLOS Computational Biology"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/12\/2571\/2479569\/neco_a_01715.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/36\/12\/2571\/2479569\/neco_a_01715.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T19:20:19Z","timestamp":1731698419000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/36\/12\/2571\/124821\/Sparse-Coding-Variational-Autoencoders"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,19]]},"references-count":89,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,11,19]]},"published-print":{"date-parts":[[2024,11,19]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01715","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,12]]},"published":{"date-parts":[[2024,11,19]]}}}