{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T09:31:39Z","timestamp":1772530299434,"version":"3.50.1"},"reference-count":98,"publisher":"MIT Press","issue":"6","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,5,19]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Backpropagation of error (backprop) is a powerful algorithm for training machine learning architectures through end-to-end differentiation. Recently it has been shown that backprop in multilayer perceptrons (MLPs) can be approximated using predictive coding, a biologically plausible process theory of cortical computation that relies solely on local and Hebbian updates. The power of backprop, however, lies not in its instantiation in MLPs but in the concept of automatic differentiation, which allows for the optimization of any differentiable program expressed as a computation graph. Here, we demonstrate that predictive coding converges asymptotically (and in practice, rapidly) to exact backprop gradients on arbitrary computation graphs using only local learning rules. We apply this result to develop a straightforward strategy to translate core machine learning architectures into their predictive coding equivalents. We construct predictive coding convolutional neural networks, recurrent neural networks, and the more complex long short-term memory, which include a nonlayer-like branching internal graph structure and multiplicative interactions. Our models perform equivalently to backprop on challenging machine learning benchmarks while using only local and (mostly) Hebbian plasticity. Our method raises the potential that standard machine learning algorithms could in principle be directly implemented in neural circuitry and may also contribute to the development of completely distributed neuromorphic architectures.<\/jats:p>","DOI":"10.1162\/neco_a_01497","type":"journal-article","created":{"date-parts":[[2022,5,9]],"date-time":"2022-05-09T23:29:14Z","timestamp":1652138954000},"page":"1329-1368","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":40,"title":["Predictive Coding Approximates Backprop Along Arbitrary Computation Graphs"],"prefix":"10.1162","volume":"34","author":[{"given":"Beren","family":"Millidge","sequence":"first","affiliation":[{"name":"School of Informatics, University of Edinburgh, Edinburgh EH8 9AB, U.K. s1686853@sms.ed.ac.uk"}]},{"given":"Alexander","family":"Tschantz","sequence":"additional","affiliation":[{"name":"Sackler Center for Consciousness Science, School of Engineering and Informatics, University of Sussex, Brighton BN1 9QJ, U.K. tschantz.alec@gmail.com"}]},{"given":"Christopher L.","family":"Buckley","sequence":"additional","affiliation":[{"name":"Evolutionary and Adaptive Systems Research Group, School of Engineering and Informatics, University of Sussex, Brighton BN1 9QJ, U.K. C.L.Buckley@sussex.ac.uk"}]}],"member":"281","published-online":{"date-parts":[[2022,5,19]]},"reference":[{"key":"2022051920100593300_B1","first-page":"974","volume-title":"Advances in neural information processing systems, 32","author":"Akrout","year":"2019"},{"issue":"9","key":"2022051920100593300_B2","doi-asserted-by":"publisher","first-page":"1379","DOI":"10.1016\/0893-6080(95)00003-8","article-title":"Information geometry of the EM and EM algorithms for neural networks","volume":"8","author":"Amari","year":"1995","journal-title":"Neural Networks"},{"key":"2022051920100593300_B3","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2019.00018","article-title":"Deep learning with asymmetric connections and Hebbian updates","volume":"13","author":"Amit","year":"2019","journal-title":"Frontiers in Computational Neuroscience"},{"key":"2022051920100593300_B4","author":"Amos","year":"2019","journal-title":"The differentiable cross-entropy method"},{"key":"2022051920100593300_B5","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.cortex.2015.11.024","article-title":"Repetition suppression and its contextual determinants in predictive coding","volume":"80","author":"Auksztulewicz","year":"2016","journal-title":"Cortex"},{"key":"2022051920100593300_B6","first-page":"209","volume-title":"Information processing in the nervous system","author":"Barlow","year":"1969"},{"issue":"4","key":"2022051920100593300_B7","doi-asserted-by":"publisher","first-page":"695","DOI":"10.1016\/j.neuron.2012.10.038","article-title":"Canonical microcircuits for predictive coding","volume":"76","author":"Bastos","year":"2012","journal-title":"Neuron"},{"issue":"1","key":"2022051920100593300_B8","first-page":"5595","article-title":"Automatic differentiation in machine learning: A survey","volume":"18","author":"Baydin","year":"2017","journal-title":"Journal of Machine Learning Research"},{"key":"2022051920100593300_B9","author":"Beal","year":"2003","journal-title":"Variational algorithms for approximate Bayesian inference"},{"key":"2022051920100593300_B10","author":"Bengio","year":"2015","journal-title":"Early inference in energy-based models approximates back-propagation"},{"issue":"3","key":"2022051920100593300_B11","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1162\/NECO_a_00934","article-title":"STDP-compatible approximation of backpropagation in an energy-based model","volume":"29","author":"Bengio","year":"2017","journal-title":"Neural Computation"},{"issue":"518","key":"2022051920100593300_B12","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1080\/01621459.2017.1285773","article-title":"Variational inference: A review for statisticians","volume":"112","author":"Blei","year":"2017","journal-title":"Journal of the American Statistical Association"},{"key":"2022051920100593300_B13","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.jmp.2015.11.003","article-title":"A tutorial on the free-energy framework for modelling perception and learning","volume":"76","author":"Bogacz","year":"2017","journal-title":"Journal of Mathematical Psychology"},{"key":"2022051920100593300_B14","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.jmp.2017.09.004","article-title":"The free energy principle for action and perception: A mathematical review","volume":"81","author":"Buckley","year":"2017","journal-title":"Journal of Mathematical Psychology"},{"key":"2022051920100593300_B15","doi-asserted-by":"crossref","DOI":"10.1093\/acprof:oso\/9780195301069.001.0001","volume-title":"Rhythms of the brain","author":"Buzsaki","year":"2006"},{"key":"2022051920100593300_B16","first-page":"1683","article-title":"Stochastic gradient Hamiltonian Monte Carlo","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Chen","year":"2014"},{"key":"2022051920100593300_B17","first-page":"6571","volume-title":"Advances in neural information processing systems, 31","author":"Chen","year":"2018"},{"issue":"6203","key":"2022051920100593300_B18","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1038\/337129a0","article-title":"The recent excitement about neural networks","volume":"337","author":"Crick","year":"1989","journal-title":"Nature"},{"issue":"1","key":"2022051920100593300_B19","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MM.2018.112130359","article-title":"Loihi: A neuromorphic manycore processor with on-chip learning","volume":"38","author":"Davies","year":"2018","journal-title":"IEEE Micro"},{"key":"2022051920100593300_B20","doi-asserted-by":"publisher","DOI":"10.3389\/fnbot.2019.00006","article-title":"A differentiable physics engine for deep learning in robotics","volume":"13","author":"Degrave","year":"2019","journal-title":"Frontiers in Neurorobotics"},{"issue":"374","key":"2022051920100593300_B21","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1080\/01621459.1981.10477653","article-title":"Estimation in covariance components models","volume":"76","author":"Dempster","year":"1981","journal-title":"Journal of the American Statistical Association"},{"key":"2022051920100593300_B22","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.neuroimage.2016.10.001","article-title":"Seeing it all: Convolutional network layers map the function of the human visual system","volume":"152","author":"Eickenberg","year":"2017","journal-title":"NeuroImage"},{"issue":"1","key":"2022051920100593300_B23","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/TIT.1955.1055126","article-title":"Predictive coding\u2013I","volume":"1","author":"Elias","year":"1955","journal-title":"IRE Transactions on Information Theory"},{"key":"2022051920100593300_B24","doi-asserted-by":"publisher","DOI":"10.3389\/fnhum.2010.00215","article-title":"Attention, uncertainty, and free-energy","volume":"4","author":"Feldman","year":"2010","journal-title":"Frontiers in Human Neuroscience"},{"issue":"9","key":"2022051920100593300_B25","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1016\/j.neunet.2003.06.005","article-title":"Learning and inference in the brain","volume":"16","author":"Friston","year":"2003","journal-title":"Neural Networks"},{"issue":"1456","key":"2022051920100593300_B26","doi-asserted-by":"publisher","first-page":"815","DOI":"10.1098\/rstb.2005.1622","article-title":"A theory of cortical responses","volume":"360","author":"Friston","year":"2005","journal-title":"Philosophical Transactions of the Royal Society B: Biological Sciences"},{"key":"2022051920100593300_B27","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1000211","article-title":"Hierarchical models in the brain","volume-title":"PLOS Computational Biology","author":"Friston","year":"2008"},{"issue":"1","key":"2022051920100593300_B28","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.neuroimage.2006.08.035","article-title":"Variational free energy and the Laplace approximation","volume":"34","author":"Friston","year":"2007","journal-title":"NeuroImage"},{"issue":"5","key":"2022051920100593300_B29","doi-asserted-by":"publisher","first-page":"652","DOI":"10.1109\/JPROC.2014.2304638","article-title":"The spinnaker project","volume":"102","author":"Furber","year":"2014","journal-title":"Proceedings of the IEEE"},{"key":"2022051920100593300_B30","first-page":"2672","volume-title":"Advances in neural information processing systems, 27","author":"Goodfellow","year":"2014"},{"issue":"6","key":"2022051920100593300_B31","first-page":"83","article-title":"On automatic differentiation","volume":"6","author":"Griewank","year":"1989","journal-title":"Mathematical programming: Recent developments and applications"},{"key":"2022051920100593300_B32","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.22901","article-title":"Towards deep learning with segregated dendrites","volume":"6","author":"Guerguiev","year":"2017","journal-title":"eLife"},{"issue":"358","key":"2022051920100593300_B33","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1080\/01621459.1977.10480998","article-title":"Maximum likelihood approaches to variance component estimation and to related problems","volume":"72","author":"Harville","year":"1977","journal-title":"Journal of the American Statistical Association"},{"issue":"2","key":"2022051920100593300_B34","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"},{"key":"2022051920100593300_B35","volume-title":"On intelligence: How a new understanding of the brain will lead to the creation of truly intelligent machines","author":"Hawkins","year":"2007"},{"key":"2022051920100593300_B36","first-page":"770","article-title":"Deep residual learning for image recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"He","year":"2016"},{"key":"2022051920100593300_B37","article-title":"Real2sim transfer using differentiable physics","author":"Heiden","year":"2019","journal-title":"Workshop on Closing the Reality Gap in sim2real Transfer for Robotic Manipulation."},{"issue":"8","key":"2022051920100593300_B38","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter","year":"1997","journal-title":"Neural Computation"},{"issue":"3","key":"2022051920100593300_B39","doi-asserted-by":"publisher","first-page":"687","DOI":"10.1016\/j.cognition.2008.05.010","article-title":"Predictive coding explains binocular rivalry: An epistemological review","volume":"108","author":"Hohwy","year":"2008","journal-title":"Cognition"},{"key":"2022051920100593300_B40","author":"Innes","year":"2019","journal-title":"Zygote: A differentiable programming system to bridge machine learning and scientific computing"},{"issue":"1668","key":"2022051920100593300_B41","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2014.0169","article-title":"Cerebral hierarchies: Predictive processing, precision and the pulvinar","volume":"370","author":"Kanai","year":"2015","journal-title":"Philosophical Transactions of the Royal Society B: Biological Sciences"},{"key":"2022051920100593300_B42","author":"Kaplan","year":"2020","journal-title":"Scaling laws for neural language models"},{"issue":"407","key":"2022051920100593300_B43","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1080\/01621459.1989.10478825","article-title":"Approximate Bayesian inference in conditionally independent hierarchical models (parametric empirical Bayes models)","volume":"84","author":"Kass","year":"1989","journal-title":"Journal of the American Statistical Association"},{"issue":"11","key":"2022051920100593300_B44","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1003915","article-title":"Deep supervised, but not unsupervised, models may explain it cortical representation","volume":"10","author":"Khaligh-Razavi","year":"2014","journal-title":"PLOS Computational Biology"},{"key":"2022051920100593300_B45","first-page":"1097","volume-title":"Advances in neural information processing systems, 25","author":"Krizhevsky","year":"2012"},{"key":"2022051920100593300_B46","doi-asserted-by":"crossref","first-page":"498","DOI":"10.1007\/978-3-319-23528-8_31","article-title":"Difference target propagation","volume-title":"Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases","author":"Lee","year":"2015"},{"key":"2022051920100593300_B47","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10279","article-title":"How important is weight symmetry in backpropagation?","volume-title":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence.","author":"Liao","year":"2016"},{"issue":"1","key":"2022051920100593300_B48","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/ncomms13276","article-title":"Random synaptic feedback weights support error backpropagation for deep learning","volume":"7","author":"Lillicrap","year":"2016","journal-title":"Nature Communications"},{"key":"2022051920100593300_B49","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.conb.2019.01.011","article-title":"Backpropagation through time and the brain","volume":"55","author":"Lillicrap","year":"2019","journal-title":"Current Opinion in Neurobiology"},{"key":"2022051920100593300_B50","doi-asserted-by":"publisher","first-page":"1","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":"2022051920100593300_B51","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1162\/jocn_a_01544","article-title":"Convolutional neural networks as a model of the visual system: Past, present, and future","volume":"33","author":"Lindsay","year":"2020","journal-title":"Journal of Cognitive Neuroscience"},{"key":"2022051920100593300_B52","author":"Linnainmaa","year":"1970","journal-title":"The representation of the cumulative rounding error of an algorithm as a Taylor expansion of the local rounding errors"},{"key":"2022051920100593300_B53","author":"Lotter","year":"2016","journal-title":"Deep predictive coding networks for video prediction and unsupervised learning"},{"issue":"1","key":"2022051920100593300_B54","first-page":"4873","article-title":"Stochastic gradient descent as approximate Bayesian inference","volume":"18","author":"Mandt","year":"2017","journal-title":"Journal of Machine Learning Research"},{"issue":"6197","key":"2022051920100593300_B55","doi-asserted-by":"publisher","first-page":"668","DOI":"10.1126\/science.1254642","article-title":"A million spiking-neuron integrated circuit with a scalable communication network and interface","volume":"345","author":"Merolla","year":"2014","journal-title":"Science"},{"key":"2022051920100593300_B56","author":"Millidge","year":"2021","journal-title":"Predictive coding: A theoretical and experimental review"},{"key":"2022051920100593300_B57","author":"Millidge","year":"2020","journal-title":"Relaxing the constraints on predictive coding models"},{"key":"2022051920100593300_B58","author":"Millidge","year":"2021","journal-title":"Neural Kalman filtering"},{"issue":"7540","key":"2022051920100593300_B59","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","article-title":"Human-level control through deep reinforcement learning","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"key":"2022051920100593300_B60","author":"Okada","year":"2017","journal-title":"Path integral networks: End-to-end differentiable optimal control"},{"key":"2022051920100593300_B61","author":"Ollivier","year":"2019","journal-title":"The extended Kalman filter is a natural gradient descent in trajectory space"},{"key":"2022051920100593300_B62","author":"Ollivier","year":"2015","journal-title":"Training recurrent networks online without backtracking"},{"key":"2022051920100593300_B63","doi-asserted-by":"publisher","first-page":"4267","DOI":"10.1109\/TNNLS.2019.2953622","article-title":"Continual learning of recurrent neural networks by locally aligning distributed representations","volume":"31","author":"Ororbia","year":"2020","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"2022051920100593300_B64","author":"Pal","year":"2019","journal-title":"RayTracer.jl: A differentiable renderer that supports parameter optimization for scene reconstruction"},{"key":"2022051920100593300_B65","author":"Paszke","year":"2017","journal-title":"Automatic differentiation in PyTorch"},{"key":"2022051920100593300_B66","author":"Rackauckas","year":"2019","journal-title":"DiffEqFlux.jl: A Julia library for neural differential equations"},{"issue":"8","key":"2022051920100593300_B67","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"2022051920100593300_B68","first-page":"814","article-title":"Black box variational inference","volume-title":"Proceedings of the 17th International Conference on Artificial Intelligence and Statistics","author":"Ranganath","year":"2014"},{"issue":"1","key":"2022051920100593300_B69","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1038\/4580","article-title":"Predictive coding in the visual cortex: A functional interpretation of some extra-classical receptive-field effects","volume":"2","author":"Rao","year":"1999","journal-title":"Nature Neuroscience"},{"key":"2022051920100593300_B70","author":"Revels","year":"2016","journal-title":"Forward-mode automatic differentiation in Julia"},{"issue":"11","key":"2022051920100593300_B71","doi-asserted-by":"publisher","first-page":"1761","DOI":"10.1038\/s41593-019-0520-2","article-title":"A deep learning framework for neuroscience","volume":"22","author":"Richards","year":"2019","journal-title":"Nature Neuroscience"},{"issue":"2","key":"2022051920100593300_B72","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1162\/089976699300016674","article-title":"A unifying review of linear gaussian models","volume":"11","author":"Roweis","year":"1999","journal-title":"Neural Computation"},{"issue":"6","key":"2022051920100593300_B73","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1109\/34.141559","article-title":"Comparative analysis of backpropagation and the extended Kalman filter for training multilayer perceptrons","volume":"14","author":"Ruck","year":"1992","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"1","key":"2022051920100593300_B74","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1207\/s15516709cog0901_5","article-title":"Feature discovery by competitive learning","volume":"9","author":"Rumelhart","year":"1985","journal-title":"Cognitive Science"},{"key":"2022051920100593300_B75","first-page":"8721","volume-title":"Advances in neural information processing systems, 31","author":"Sacramento","year":"2018"},{"key":"2022051920100593300_B76","author":"Salvatori","year":"2021","journal-title":"Predictive coding can do exact backpropagation on convolutional and recurrent neural networks"},{"key":"2022051920100593300_B77","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2017.00024","article-title":"Equilibrium propagation: Bridging the gap between energy-based models and backpropagation","volume":"11","author":"Scellier","year":"2017","journal-title":"Frontiers in Computational Neuroscience"},{"key":"2022051920100593300_B78","author":"Scellier","year":"2018","journal-title":"Generalization of equilibrium propagation to vector field dynamics"},{"key":"2022051920100593300_B79","author":"Schrittwieser","year":"2019","journal-title":"Mastering Atari, Go, chess and shogi by planning with a learned model"},{"issue":"6","key":"2022051920100593300_B80","doi-asserted-by":"publisher","first-page":"1063","DOI":"10.1016\/S0896-6273(03)00761-X","article-title":"Learning in spiking neural networks by reinforcement of stochastic synaptic transmission","volume":"40","author":"Seung","year":"2003","journal-title":"Neuron"},{"key":"2022051920100593300_B81","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2016.01792","article-title":"Neural elements for predictive coding","volume":"7","author":"Shipp","year":"2016","journal-title":"Frontiers in Psychology"},{"issue":"7676","key":"2022051920100593300_B82","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","article-title":"Mastering the game of Go without human knowledge","volume":"550","author":"Silver","year":"2017","journal-title":"Nature"},{"key":"2022051920100593300_B83","doi-asserted-by":"publisher","DOI":"10.3389\/neuro.10.004.2008","article-title":"Reconciling predictive coding and biased competition models of cortical function","volume":"2","author":"Spratling","year":"2008","journal-title":"Frontiers in Computational Neuroscience"},{"issue":"1205","key":"2022051920100593300_B84","first-page":"427","article-title":"Predictive coding: A fresh view of inhibition in the retina","volume":"216","author":"Srinivasan","year":"1982","journal-title":"Proceedings of the Royal Society of London. Series B. Biological Sciences"},{"key":"2022051920100593300_B85","doi-asserted-by":"publisher","first-page":"843","DOI":"10.1109\/IJCNN.2004.1380039","article-title":"Backpropagation-decorrelation: Online recurrent learning with O(N) complexity","volume-title":"Proceedings of the 2004 IEEE International Joint Conference on Neural Networks","author":"Steil","year":"2004"},{"key":"2022051920100593300_B86","first-page":"1","article-title":"Going deeper with convolutions","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Szegedy","year":"2015"},{"issue":"12","key":"2022051920100593300_B87","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005859","article-title":"Invariant recognition drives neural representations of action sequences","volume":"13","author":"Tacchetti","year":"2017","journal-title":"PLOS Computational Biology"},{"key":"2022051920100593300_B88","author":"Tallec","year":"2017","journal-title":"Unbiased online recurrent optimization"},{"key":"2022051920100593300_B89","author":"Tzen","year":"2019","journal-title":"Neural stochastic differential equations: Deep latent gaussian models in the diffusion limit"},{"key":"2022051920100593300_B90","first-page":"5998","volume-title":"Advances in neural information processing systems, 30","author":"Vaswani","year":"2017"},{"issue":"7782","key":"2022051920100593300_B91","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"Nature"},{"key":"2022051920100593300_B92","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyg.2018.00345","article-title":"Illusory motion reproduced by deep neural networks trained for prediction","volume":"9","author":"Watanabe","year":"2018","journal-title":"Frontiers in Psychology"},{"issue":"5","key":"2022051920100593300_B93","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005536","article-title":"A predictive coding account of bistable perception: A model-based FMRI study","volume":"13","author":"Weilnhammer","year":"2017","journal-title":"PLOS Computational Biology"},{"key":"2022051920100593300_B94","doi-asserted-by":"crossref","first-page":"762","DOI":"10.1007\/BFb0006203","volume-title":"System modeling and optimization","author":"Werbos","year":"1982"},{"issue":"5","key":"2022051920100593300_B95","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1162\/NECO_a_00949","article-title":"An approximation of the error backpropagation algorithm in a predictive coding network with local Hebbian synaptic plasticity","volume":"29","author":"Whittington","year":"2017","journal-title":"Neural Computation"},{"key":"2022051920100593300_B96","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1016\/j.tics.2018.12.005","article-title":"Theories of error back-propagation in the brain","volume":"23","author":"Whittington","year":"2019","journal-title":"Trends in Cognitive Sciences"},{"issue":"2","key":"2022051920100593300_B97","doi-asserted-by":"publisher","first-page":"270","DOI":"10.1162\/neco.1989.1.2.270","article-title":"A learning algorithm for continually running fully recurrent neural networks","volume":"1","author":"Williams","year":"1989","journal-title":"Neural Computation"},{"issue":"23","key":"2022051920100593300_B98","doi-asserted-by":"publisher","first-page":"8619","DOI":"10.1073\/pnas.1403112111","article-title":"Performance-optimized hierarchical models predict neural responses in higher visual cortex","volume":"111","author":"Yamins","year":"2014","journal-title":"Proceedings of the National Academy of Sciences"}],"container-title":["Neural Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/34\/6\/1329\/2023477\/neco_a_01497.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/direct.mit.edu\/neco\/article-pdf\/34\/6\/1329\/2023477\/neco_a_01497.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,4]],"date-time":"2023-02-04T19:33:34Z","timestamp":1675539214000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/neco\/article\/34\/6\/1329\/110646\/Predictive-Coding-Approximates-Backprop-Along"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,19]]},"references-count":98,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,5,19]]},"published-print":{"date-parts":[[2022,5,19]]}},"URL":"https:\/\/doi.org\/10.1162\/neco_a_01497","relation":{},"ISSN":["0899-7667","1530-888X"],"issn-type":[{"value":"0899-7667","type":"print"},{"value":"1530-888X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,6]]},"published":{"date-parts":[[2022,5,19]]}}}