{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:46:31Z","timestamp":1778049991938,"version":"3.51.4"},"reference-count":135,"publisher":"MIT Press - Journals","issue":"10","content-domain":{"domain":["direct.mit.edu"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Convolutional neural networks (CNNs) were inspired by early findings in the study of biological vision. They have since become successful tools in computer vision and state-of-the-art models of both neural activity and behavior on visual tasks. This review highlights what, in the context of CNNs, it means to be a good model in computational neuroscience and the various ways models can provide insight. Specifically, it covers the origins of CNNs and the methods by which we validate them as models of biological vision. It then goes on to elaborate on what we can learn about biological vision by understanding and experimenting on CNNs and discusses emerging opportunities for the use of CNNs in vision research beyond basic object recognition.<\/jats:p>","DOI":"10.1162\/jocn_a_01544","type":"journal-article","created":{"date-parts":[[2020,2,6]],"date-time":"2020-02-06T17:55:13Z","timestamp":1581011713000},"page":"2017-2031","update-policy":"https:\/\/doi.org\/10.1162\/mitpressjournals.corrections.policy","source":"Crossref","is-referenced-by-count":410,"title":["Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future"],"prefix":"10.1162","volume":"33","author":[{"given":"Grace W.","family":"Lindsay","sequence":"first","affiliation":[{"name":"University College London"}]}],"member":"281","published-online":{"date-parts":[[2021,9,1]]},"reference":[{"key":"2021090816495180100_bib1","doi-asserted-by":"crossref","first-page":"e1006613","DOI":"10.1371\/journal.pcbi.1006613","article-title":"Deep convolutional networks do not classify based on global object shape","volume":"14","author":"Baker","year":"2018","journal-title":"PLoS Computational Biology"},{"key":"2021090816495180100_bib2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.conb.2017.06.003","article-title":"Recurrent neural networks as versatile tools of neuroscience research","volume":"46","author":"Barak","year":"2017","journal-title":"Current Opinion in Neurobiology"},{"key":"2021090816495180100_bib3","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.conb.2019.01.007","article-title":"Analyzing biological and artificial neural networks: Challenges with opportunities for synergy?","volume":"55","author":"Barrett","year":"2019","journal-title":"Current Opinion in Neurobiology"},{"key":"2021090816495180100_bib4","first-page":"9390","article-title":"Assessing the scalability of biologically-motivated deep learning algorithms and architectures","volume-title":"Advances in neural information processing systems","author":"Bartunov","year":"2018"},{"key":"2021090816495180100_bib5","doi-asserted-by":"crossref","first-page":"eaav9436","DOI":"10.1126\/science.aav9436","article-title":"Neural population control via deep image synthesis","volume":"364","author":"Bashivan","year":"2019","journal-title":"Science"},{"key":"2021090816495180100_bib6","doi-asserted-by":"crossref","first-page":"e1006111","DOI":"10.1371\/journal.pcbi.1006111","article-title":"Computational mechanisms underlying cortical responses to the affordance properties of visual scenes","volume":"14","author":"Bonner","year":"2018","journal-title":"PLoS Computational Biology"},{"key":"2021090816495180100_bib7","doi-asserted-by":"crossref","first-page":"6513","DOI":"10.1523\/JNEUROSCI.1714-18.2019","article-title":"The ventral visual pathway represents animal appearance over animacy, unlike human behavior and deep neural networks","volume":"39","author":"Bracci","year":"2019","journal-title":"Journal of Neuroscience"},{"key":"2021090816495180100_bib8","doi-asserted-by":"crossref","first-page":"e1006897","DOI":"10.1371\/journal.pcbi.1006897","article-title":"Deep convolutional models improve predictions of macaque V1 responses to natural images","volume":"15","author":"Cadena","year":"2019","journal-title":"PLoS Computational Biology"},{"key":"2021090816495180100_bib9","article-title":"How well do deep neural networks trained on object recognition characterize the mouse visual system?","volume-title":"NeurIPS Workshop on Real Neurons and Hidden Units","author":"Cadena","year":"2019"},{"key":"2021090816495180100_bib10","first-page":"217","article-title":"Diverse feature visualizations reveal invariances in early layers of deep neural networks","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Cadena","year":"2018"},{"key":"2021090816495180100_bib11","doi-asserted-by":"crossref","first-page":"1733","DOI":"10.1152\/jn.01265.2006","article-title":"A model of V4 shape selectivity and invariance","volume":"98","author":"Cadieu","year":"2007","journal-title":"Journal of Neurophysiology"},{"key":"2021090816495180100_bib12","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1007\/s11263-014-0788-3","article-title":"Spiking deep convolutional neural networks for energy-efficient object recognition","volume":"113","author":"Cao","year":"2015","journal-title":"International Journal of Computer Vision"},{"key":"2021090816495180100_bib13","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1038\/s41597-019-0052-3","article-title":"BOLD5000, a public fMRI dataset while viewing 5000 visual images","volume":"6","author":"Chang","year":"2019","journal-title":"Scientific Data"},{"key":"2021090816495180100_bib14","doi-asserted-by":"crossref","first-page":"031003","DOI":"10.1103\/PhysRevX.8.031003","article-title":"Classification and geometry of general perceptual manifolds","volume":"8","author":"Chung","year":"2018","journal-title":"Physical Review X"},{"key":"2021090816495180100_bib15","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.neuroimage.2016.03.063","article-title":"Dynamics of scene representations in the human brain revealed by magnetoencephalography and deep neural networks","volume":"153","author":"Cichy","year":"2017","journal-title":"Neuroimage"},{"key":"2021090816495180100_bib16","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1016\/j.neuroimage.2019.03.031","article-title":"The spatiotemporal neural dynamics underlying perceived similarity for real-world objects","volume":"194","author":"Cichy","year":"2019","journal-title":"Neuroimage"},{"key":"2021090816495180100_bib17","first-page":"644658","article-title":"Separability and geometry of object manifolds in deep neural networks","author":"Cohen","year":"2019","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib18","first-page":"2148","article-title":"Predicting parameters in deep learning","volume-title":"Advances in neural information processing systems","author":"Denil","year":"2013"},{"key":"2021090816495180100_bib19","doi-asserted-by":"crossref","first-page":"10636","DOI":"10.1038\/s41598-018-28865-1","article-title":"Integrated deep visual and semantic attractor neural networks predict fMRI pattern-information along the ventral object processing pathway","volume":"8","author":"Devereux","year":"2018","journal-title":"Scientific Reports"},{"key":"2021090816495180100_bib20","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1038\/s41593-019-0550-9","article-title":"A large-scale, standardized physiological survey reveals functional organization of the mouse visual cortex","volume":"23","author":"de Vries","year":"2019","journal-title":"Nature Neuroscience"},{"key":"2021090816495180100_bib21","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.tics.2007.06.010","article-title":"Untangling invariant object recognition","volume":"11","author":"DiCarlo","year":"2007","journal-title":"Trends in Cognitive Sciences"},{"key":"2021090816495180100_bib22","doi-asserted-by":"crossref","first-page":"65","DOI":"10.3758\/BF03211918","article-title":"Limited translation invariance of human visual pattern recognition","volume":"60","author":"Dill","year":"1998","journal-title":"Perception & Psychophysics"},{"key":"2021090816495180100_bib23","doi-asserted-by":"crossref","DOI":"10.32470\/CCN.2019.1405-0","article-title":"Why are face and object processing segregated in the human brain? Testing computational hypotheses with deep convolutional neural networks","author":"Dobs","year":"2019"},{"key":"2021090816495180100_bib24","first-page":"402735","article-title":"Task-specific vision models explain task-specific areas of visual cortex","author":"Dwivedi","year":"2018","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib25","doi-asserted-by":"crossref","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"},{"key":"2021090816495180100_bib26","doi-asserted-by":"crossref","first-page":"100","DOI":"10.1016\/j.cobeha.2019.07.004","article-title":"Learning to see stuff","volume":"30","author":"Fleming","year":"2019","journal-title":"Current Opinion in Behavioral Sciences"},{"key":"2021090816495180100_bib27","first-page":"1136","article-title":"Input switched affine networks: An RNN architecture designed for interpretability","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Foerster","year":"2017"},{"key":"2021090816495180100_bib28","doi-asserted-by":"crossref","first-page":"5397","DOI":"10.1038\/s41598-018-23618-6","article-title":"Using human brain activity to guide machine learning","volume":"8","author":"Fong","year":"2018","journal-title":"Scientific Reports"},{"key":"2021090816495180100_bib29","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","author":"Frankle","year":"2018","journal-title":"arXiv preprint arXiv:1803.03635"},{"key":"2021090816495180100_bib30","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1007\/BF00344251","article-title":"Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position","volume":"36","author":"Fukushima","year":"1980","journal-title":"Biological Cybernetics"},{"key":"2021090816495180100_bib31","article-title":"Weight agnostic neural networks","author":"Gaier","year":"2019","journal-title":"arXiv preprint arXiv:1906.04358"},{"key":"2021090816495180100_bib32","article-title":"Comparing deep neural networks against humans: Object recognition when the signal gets weaker","author":"Geirhos","year":"2017","journal-title":"arXiv preprint arXiv:1706.06969"},{"key":"2021090816495180100_bib33","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","author":"Geirhos","year":"2018","journal-title":"arXiv preprint arXiv:1811.12231"},{"key":"2021090816495180100_bib34","first-page":"7538","article-title":"Generalisation in humans and deep neural networks","volume-title":"Advances in neural information processing systems","author":"Geirhos","year":"2018"},{"key":"2021090816495180100_bib35","doi-asserted-by":"crossref","first-page":"74","DOI":"10.3389\/fncom.2014.00074","article-title":"Feedforward object-vision models only tolerate small image variations compared to human","volume":"8","author":"Ghodrati","year":"2014","journal-title":"Frontiers in Computational Neuroscience"},{"key":"2021090816495180100_bib36","article-title":"Controversial stimuli: Pitting neural networks against each other as models of human recognition","author":"Golan","year":"2019","journal-title":"arXiv preprint arXiv:1911.09288"},{"key":"2021090816495180100_bib37","doi-asserted-by":"crossref","first-page":"10005","DOI":"10.1523\/JNEUROSCI.5023-14.2015","article-title":"Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream","volume":"35","author":"G\u00fc\u00e7l\u00fc","year":"2015","journal-title":"Journal of Neuroscience"},{"key":"2021090816495180100_bib38","first-page":"767285","article-title":"Learning divisive normalization in primary visual cortex","author":"G\u00fcnthner","year":"2019","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib39","first-page":"15877","article-title":"Surround modulation: A bio-inspired connectivity structure for convolutional neural networks","volume-title":"Advances in neural information processing systems","author":"Hasani","year":"2019"},{"key":"2021090816495180100_bib40","first-page":"764258","article-title":"Robust-fit to nature: An evolutionary perspective on biological (and artificial) neural networks","author":"Hasson","year":"2019","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib41","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1038\/nn.4247","article-title":"Explicit information for category-orthogonal object properties increases along the ventral stream","volume":"19","author":"Hong","year":"2016","journal-title":"Nature Neuroscience"},{"key":"2021090816495180100_bib42","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1113\/jphysiol.1962.sp006837","article-title":"Receptive fields, binocular interaction and functional architecture in the cat's visual cortex","volume":"160","author":"Hubel","year":"1962","journal-title":"Journal of Physiology"},{"key":"2021090816495180100_bib43","first-page":"860759","article-title":"Do deep neural networks see the way we do?","author":"Jacob","year":"2019","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib44","doi-asserted-by":"crossref","first-page":"e47596","DOI":"10.7554\/eLife.47596","article-title":"Population response magnitude variation in inferotemporal cortex predicts image memorability","volume":"8","author":"Jaegle","year":"2019","journal-title":"eLife"},{"key":"2021090816495180100_bib45","first-page":"395","article-title":"Incorporating feedback in convolutional neural networks","volume-title":"Proceedings of the Cognitive Computational Neuroscience Conference","author":"Jarvers","year":"2019"},{"key":"2021090816495180100_bib46","doi-asserted-by":"crossref","first-page":"1726","DOI":"10.3389\/fpsyg.2017.01726","article-title":"Deep convolutional neural networks outperform feature-based but not categorical models in explaining object similarity judgments","volume":"8","author":"Jozwik","year":"2017","journal-title":"Frontiers in Psychology"},{"key":"2021090816495180100_bib47","doi-asserted-by":"crossref","first-page":"974","DOI":"10.1038\/s41593-019-0392-5","article-title":"Evidence that recurrent circuits are critical to the ventral stream's execution of core object recognition behavior","volume":"22","author":"Kar","year":"2019","journal-title":"Nature Neuroscience"},{"key":"2021090816495180100_bib48","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.neuroimage.2017.08.016","article-title":"Principles for models of neural information processing","volume":"180","author":"Kay","year":"2018","journal-title":"Neuroimage"},{"key":"2021090816495180100_bib49","doi-asserted-by":"crossref","first-page":"630","DOI":"10.1016\/j.neuron.2018.03.044","article-title":"A task-optimized neural network replicates human auditory behavior, predicts brain responses, and reveals a cortical processing hierarchy","volume":"98","author":"Kell","year":"2018","journal-title":"Neuron"},{"key":"2021090816495180100_bib50","doi-asserted-by":"crossref","first-page":"e1003915","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":"2021090816495180100_bib51","doi-asserted-by":"crossref","first-page":"32672","DOI":"10.1038\/srep32672","article-title":"Deep networks can resemble human feed-forward vision in invariant object recognition","volume":"6","author":"Kheradpisheh","year":"2016","journal-title":"Scientific Reports"},{"key":"2021090816495180100_bib52","doi-asserted-by":"crossref","DOI":"10.1093\/acrefore\/9780190264086.013.46","article-title":"Deep neural networks in computational neuroscience","volume-title":"Oxford research encyclopedia of neuroscience","author":"Kietzmann","year":"2019"},{"key":"2021090816495180100_bib53","article-title":"Disentangling neural mechanisms for perceptual grouping","author":"Kim","year":"2019","journal-title":"arXiv preprint arXiv:1906.01558"},{"key":"2021090816495180100_bib54","article-title":"Do neural networks show Gestalt phenomena? An exploration of the law of closure","author":"Kim","year":"2019","journal-title":"arXiv preprint arXiv:1903.01069"},{"key":"2021090816495180100_bib55","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1167\/19.4.29","article-title":"Using deep learning to probe the neural code for images in primary visual cortex","volume":"19","author":"Kindel","year":"2019","journal-title":"Journal of Vision"},{"key":"2021090816495180100_bib56","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1016\/j.neuroimage.2019.04.079","article-title":"Similarity judgments and cortical visual responses reflect different properties of object and scene categories in naturalistic images","volume":"197","author":"King","year":"2019","journal-title":"Neuroimage"},{"key":"2021090816495180100_bib60","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"Proceedings of the 36th International Conference on Machine Learning","author":"Kornblith","year":"2019"},{"key":"2021090816495180100_bib57","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1146\/annurev-vision-082114-035447","article-title":"Deep neural networks: A new framework for modeling biological vision and brain information processing","volume":"1","author":"Kriegeskorte","year":"2015","journal-title":"Annual Review of Vision Science"},{"key":"2021090816495180100_bib58","doi-asserted-by":"crossref","first-page":"R231","DOI":"10.1016\/j.cub.2019.02.034","article-title":"Neural network models and deep learning","volume":"29","author":"Kriegeskorte","year":"2019","journal-title":"Current Biology"},{"key":"2021090816495180100_bib59","first-page":"4","article-title":"Representational similarity analysis\u2014Connecting the branches of systems neuroscience","volume":"2","author":"Kriegeskorte","year":"2008","journal-title":"Frontiers in Systems Neuroscience"},{"key":"2021090816495180100_bib61","doi-asserted-by":"crossref","first-page":"e1004896","DOI":"10.1371\/journal.pcbi.1004896","article-title":"Deep neural networks as a computational model for human shape sensitivity","volume":"12","author":"Kubilius","year":"2016","journal-title":"PLoS Computational Biology"},{"key":"2021090816495180100_bib62","article-title":"Brain-like object recognition with high-performing shallow recurrent ANNs","author":"Kubilius","year":"2019","journal-title":"arXiv preprint arXiv:1909.06161"},{"key":"2021090816495180100_bib63","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1017\/S0140525X16001837","article-title":"Building machines that learn and think like people","volume":"40","author":"Lake","year":"2017","journal-title":"Behavioral and Brain Sciences"},{"key":"2021090816495180100_bib64","article-title":"Deep neural networks predict category typicality ratings for images","volume-title":"Proceedings of the 37th Annual Conference of the Cognitive Science Society","author":"Lake","year":"2015"},{"key":"2021090816495180100_bib65","doi-asserted-by":"crossref","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"LeCun","year":"1989","journal-title":"Neural Computation"},{"key":"2021090816495180100_bib66","article-title":"What does it mean to understand a neural network?","author":"Lillicrap","year":"2019","journal-title":"arXiv preprint arXiv:1907.06374"},{"key":"2021090816495180100_bib67","doi-asserted-by":"crossref","first-page":"e38105","DOI":"10.7554\/eLife.38105","article-title":"How biological attention mechanisms improve task performance in a large-scale visual system model","volume":"7","author":"Lindsay","year":"2018","journal-title":"eLife"},{"key":"2021090816495180100_bib68","first-page":"875534","article-title":"A simple circuit model of visual cortex explains neural and behavioral aspects of attention","author":"Lindsay","year":"2019","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib69","first-page":"511535","article-title":"A unified theory of early visual representations from retina to cortex through anatomically constrained deep CNNs","author":"Lindsey","year":"2019","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib70","article-title":"Deep predictive coding networks for video prediction and unsupervised learning","author":"Lotter","year":"2016","journal-title":"arXiv preprint arXiv:1605.08104"},{"key":"2021090816495180100_bib71","first-page":"1457","article-title":"Deep networks as models of human and animal categorization","volume-title":"Proceedings of the 39th Annual Meeting of the Cognitive Science Society","author":"Love","year":"2017"},{"key":"2021090816495180100_bib72","first-page":"340943","article-title":"Deep learning models reveal internal structure and diverse computations in the retina under natural scenes","author":"Maheswaranathan","year":"2018","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib73","first-page":"20150203","article-title":"Understanding deep convolutional networks","volume":"374","author":"Mallat","year":"2016","journal-title":"Philosophical Transactions of the Royal Society of London, Series A: Mathematical, Physical and Engineering Sciences"},{"key":"2021090816495180100_bib74","first-page":"1649","article-title":"Nonlinear processing of shape information in rat lateral extrastriate cortex","volume":"39","author":"Matteucci","year":"2019","journal-title":"Journal of Neuroscience"},{"key":"2021090816495180100_bib75","first-page":"1361","article-title":"Deep learning models of the retinal response to natural scenes","volume-title":"Advances in neural information processing systems","author":"McIntosh","year":"2016"},{"key":"2021090816495180100_bib76","article-title":"Hierarchical visuomotor control of humanoids","author":"Merel","year":"2018","journal-title":"arXiv preprint arXiv:1811.09656"},{"key":"2021090816495180100_bib77","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Advances in neural information processing systems","author":"Mnih","year":"2014"},{"key":"2021090816495180100_bib78","article-title":"KerCNNs: Biologically inspired lateral connections for classification of corrupted images","author":"Montobbio","year":"2019","journal-title":"arXiv preprint arXiv:1910.08336"},{"key":"2021090816495180100_bib79","article-title":"On the importance of single directions for generalization","author":"Morcos","year":"2018","journal-title":"arXiv preprint arXiv:1803.06959"},{"key":"2021090816495180100_bib80","article-title":"A balanced comparison of object invariances in monkey IT neurons","volume":"4","author":"Murty","year":"2017","journal-title":"eNeuro"},{"key":"2021090816495180100_bib81","doi-asserted-by":"crossref","first-page":"E3276","DOI":"10.1073\/pnas.1714287115","article-title":"Multiplicative mixing of object identity and image attributes in single inferior temporal neurons","volume":"115","author":"Murty","year":"2018","journal-title":"Proceedings of the National Academy of Sciences, U.S.A."},{"key":"2021090816495180100_bib82","article-title":"Understanding neural networks via feature visualization: A survey","author":"Nguyen","year":"2019","journal-title":"arXiv preprint arXiv:1904.08939"},{"key":"2021090816495180100_bib83","doi-asserted-by":"crossref","first-page":"e7","DOI":"10.23915\/distill.00007","article-title":"Feature visualization","volume":"2","author":"Olah","year":"2017","journal-title":"Distill"},{"key":"2021090816495180100_bib84","article-title":"One-shot high-fidelity imitation: Training large-scale deep nets with RL","author":"Paine","year":"2018","journal-title":"arXiv preprint arXiv:1810.05017"},{"key":"2021090816495180100_bib85","doi-asserted-by":"crossref","first-page":"2648","DOI":"10.1111\/cogs.12670","article-title":"Evaluating (and improving) the correspondence between deep neural networks and human representations","volume":"42","author":"Peterson","year":"2018","journal-title":"Cognitive Science"},{"key":"2021090816495180100_bib86","doi-asserted-by":"crossref","first-page":"e27","DOI":"10.1371\/journal.pcbi.0040027","article-title":"Why is real-world visual object recognition hard?","volume":"4","author":"Pinto","year":"2008","journal-title":"PLoS Computational Biology"},{"key":"2021090816495180100_bib87","doi-asserted-by":"crossref","first-page":"e1007001","DOI":"10.1371\/journal.pcbi.1007001","article-title":"Beyond core object recognition: Recurrent processes account for object recognition under occlusion","volume":"15","author":"Rajaei","year":"2019","journal-title":"PLoS Computational Biology"},{"key":"2021090816495180100_bib88","doi-asserted-by":"crossref","first-page":"7255","DOI":"10.1523\/JNEUROSCI.0388-18.2018","article-title":"Large-scale, high-resolution comparison of the core visual object recognition behavior of humans, monkeys, and state-of-the-art deep artificial neural networks","volume":"38","author":"Rajalingham","year":"2018","journal-title":"Journal of Neuroscience"},{"key":"2021090816495180100_bib89","doi-asserted-by":"crossref","first-page":"2352","DOI":"10.1162\/neco_a_00990","article-title":"Deep convolutional neural networks for image classification: A comprehensive review","volume":"29","author":"Rawat","year":"2017","journal-title":"Neural Computation"},{"key":"2021090816495180100_bib90","doi-asserted-by":"crossref","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"},{"key":"2021090816495180100_bib91","doi-asserted-by":"crossref","DOI":"10.21236\/ADA458109","volume-title":"Computational models of object recognition in cortex: A review","author":"Riesenhuber","year":"2000"},{"key":"2021090816495180100_bib92","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.tics.2009.11.005","article-title":"Perceptual learning rules based on reinforcers and attention","volume":"14","author":"Roelfsema","year":"2010","journal-title":"Trends in Cognitive Sciences"},{"key":"2021090816495180100_bib93","first-page":"1961","article-title":"Totally looks like\u2014How humans compare, compared to machines","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","author":"Rosenfeld","year":"2018"},{"key":"2021090816495180100_bib94","article-title":"Effects of degradations on deep neural network architectures","author":"Roy","year":"2018","journal-title":"arXiv preprint arXiv:1807.10108"},{"key":"2021090816495180100_bib95","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1016\/j.neuron.2014.12.026","article-title":"The stabilized supralinear network: A unifying circuit motif underlying multi-input integration in sensory cortex","volume":"85","author":"Rubin","year":"2015","journal-title":"Neuron"},{"key":"2021090816495180100_bib96","first-page":"8735","article-title":"Dendritic cortical microcircuits approximate the backpropagation algorithm","volume-title":"Advances in neural information processing systems","author":"Sacramento","year":"2018"},{"key":"2021090816495180100_bib97","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1146\/annurev-statistics-010814-020120","article-title":"Learning deep generative models","volume":"2","author":"Salakhutdinov","year":"2015","journal-title":"Annual Review of Statistics and Its Application"},{"key":"2021090816495180100_bib98","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/978-3-030-28954-6_1","article-title":"Towards explainable artificial intelligence","volume-title":"Explainable AI: Interpreting, explaining and visualizing deep learning","author":"Samek","year":"2019"},{"key":"2021090816495180100_bib99","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"Saxe","year":"2013","journal-title":"arXiv preprint arXiv:1312.6120"},{"key":"2021090816495180100_bib100","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.cortex.2017.09.019","article-title":"Visual pathways from the perspective of cost functions and multi-task deep neural networks","volume":"98","author":"Scholte","year":"2018","journal-title":"Cortex"},{"key":"2021090816495180100_bib101","first-page":"407007","article-title":"Brain-Score: Which artificial neural network for object recognition is most brain-like?","author":"Schrimpf","year":"2018","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib102","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1016\/j.neuroimage.2017.07.018","article-title":"Convolutional neural network-based encoding and decoding of visual object recognition in space and time","volume":"180","author":"Seeliger","year":"2018","journal-title":"Neuroimage"},{"key":"2021090816495180100_bib103","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1146\/annurev-vision-091718-014951","article-title":"Deep learning: The good, the bad, and the ugly","volume":"5","author":"Serre","year":"2019","journal-title":"Annual Review of Vision Science"},{"key":"2021090816495180100_bib104","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/S0079-6123(06)65004-8","article-title":"A quantitative theory of immediate visual recognition","volume":"165","author":"Serre","year":"2007","journal-title":"Progress in Brain Research"},{"key":"2021090816495180100_bib105","doi-asserted-by":"crossref","first-page":"e1006633","DOI":"10.1371\/journal.pcbi.1006633","article-title":"Deep image reconstruction from human brain activity","volume":"15","author":"Shen","year":"2019","journal-title":"PLoS Computational Biology"},{"key":"2021090816495180100_bib106","doi-asserted-by":"crossref","first-page":"2269","DOI":"10.1002\/hbm.24006","article-title":"Deep recurrent neural network reveals a hierarchy of process memory during dynamic natural vision","volume":"39","author":"Shi","year":"2018","journal-title":"Human Brain Mapping"},{"key":"2021090816495180100_bib107","doi-asserted-by":"crossref","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"},{"key":"2021090816495180100_bib108","first-page":"7199","article-title":"Stimulus domain transfer in recurrent models for large scale cortical population prediction on video","volume-title":"Advances in neural information processing systems","author":"Sinz","year":"2018"},{"key":"2021090816495180100_bib109","first-page":"677237","article-title":"Recurrent networks can recycle neural resources to flexibly trade speed for accuracy in visual recognition","author":"Spoerer","year":"2019","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib110","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.3389\/fpsyg.2017.01551","article-title":"Recurrent convolutional neural networks: A better model of biological object recognition","volume":"8","author":"Spoerer","year":"2017","journal-title":"Frontiers in Psychology"},{"key":"2021090816495180100_bib111","article-title":"Deep learning for cognitive neuroscience","volume-title":"The cognitive neurosciences","author":"Storrs","year":"2019","edition":"6th ed."},{"key":"2021090816495180100_bib112","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1162\/NECO_a_00409","article-title":"Opening the black box: Low-dimensional dynamics in high-dimensional recurrent neural networks","volume":"25","author":"Sussillo","year":"2013","journal-title":"Neural Computation"},{"key":"2021090816495180100_bib113","doi-asserted-by":"crossref","first-page":"e1005859","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":"2021090816495180100_bib114","doi-asserted-by":"crossref","first-page":"8835","DOI":"10.1073\/pnas.1719397115","article-title":"Recurrent computations for visual pattern completion","volume":"115","author":"Tang","year":"2018","journal-title":"Proceedings of the National Academy of Sciences, U.S.A."},{"key":"2021090816495180100_bib115","article-title":"How can deep learning advance computational modeling of sensory information processing?","author":"Thompson","year":"2018","journal-title":"arXiv preprint arXiv:1810.08651"},{"key":"2021090816495180100_bib116","article-title":"The functional role of cue-driven feature-based feedback in object recognition","author":"Thorat","year":"2019","journal-title":"arXiv preprint arXiv:1903.10446"},{"key":"2021090816495180100_bib117","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/ITW.2015.7133169","article-title":"Deep learning and the information bottleneck principle","volume-title":"2015 IEEE Information Theory Workshop (ITW)","author":"Tishby","year":"2015"},{"key":"2021090816495180100_bib118","doi-asserted-by":"crossref","first-page":"3551","DOI":"10.1109\/IJCNN.2017.7966303","article-title":"Similarities and differences between stimulus tuning in the inferotemporal visual cortex and convolutional networks","volume-title":"2017 International Joint Conference on Neural Networks (IJCNN)","author":"Tripp","year":"2017"},{"key":"2021090816495180100_bib119","article-title":"A connectome based hexagonal lattice convolutional network model of the Drosophila visual system","author":"Tschopp","year":"2018","journal-title":"arXiv preprint arXiv:1806.04793"},{"key":"2021090816495180100_bib120","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1038\/s41593-018-0284-0","article-title":"Stimulus- and goal-oriented frameworks for understanding natural vision","volume":"22","author":"Turner","year":"2019","journal-title":"Nature Neuroscience"},{"key":"2021090816495180100_bib121","first-page":"2033","article-title":"Attentional neural network: Feature selection using cognitive feedback","volume-title":"Advances in neural information processing systems","author":"Wang","year":"2014"},{"key":"2021090816495180100_bib122","doi-asserted-by":"crossref","first-page":"345","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"},{"key":"2021090816495180100_bib123","doi-asserted-by":"crossref","first-page":"3752","DOI":"10.1038\/s41598-018-22160-9","article-title":"Deep residual network predicts cortical representation and organization of visual features for rapid categorization","volume":"8","author":"Wen","year":"2018","journal-title":"Scientific Reports"},{"key":"2021090816495180100_bib124","doi-asserted-by":"crossref","first-page":"6028","DOI":"10.1523\/JNEUROSCI.1620-17.2018","article-title":"Deep neural networks for modeling visual perceptual learning","volume":"38","author":"Wenliang","year":"2018","journal-title":"Journal of Neuroscience"},{"key":"2021090816495180100_bib125","doi-asserted-by":"crossref","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"},{"key":"2021090816495180100_bib126","doi-asserted-by":"crossref","first-page":"36","DOI":"10.2352\/ISSN.2470-1173.2017.14.HVEI-113","article-title":"Methods and measurements to compare men against machines","volume":"2017","author":"Wichmann","year":"2017","journal-title":"Electronic Imaging, Human Vision and Electronic Imaging"},{"key":"2021090816495180100_bib127","doi-asserted-by":"crossref","first-page":"674","DOI":"10.3389\/fpsyg.2014.00674","article-title":"Early recurrent feedback facilitates visual object recognition under challenging conditions","volume":"5","author":"Wyatte","year":"2014","journal-title":"Frontiers in Psychology"},{"key":"2021090816495180100_bib128","doi-asserted-by":"crossref","first-page":"356","DOI":"10.1038\/nn.4244","article-title":"Using goal-driven deep learning models to understand sensory cortex","volume":"19","author":"Yamins","year":"2016","journal-title":"Nature Neuroscience"},{"key":"2021090816495180100_bib129","doi-asserted-by":"crossref","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, U.S.A."},{"key":"2021090816495180100_bib130","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1007\/978-3-319-10590-1_53","article-title":"Visualizing and understanding convolutional networks","volume-title":"13th European Conference on Computer Vision, ECCV 2014","author":"Zeiler","year":"2014"},{"key":"2021090816495180100_bib131","first-page":"555193","article-title":"Orthogonal representations of object shape and category in deep convolutional neural networks and human visual cortex","author":"Zeman","year":"2019","journal-title":"bioRxiv"},{"key":"2021090816495180100_bib132","article-title":"Revisiting the importance of individual units in CNNs via ablation","author":"Zhou","year":"2018","journal-title":"arXiv preprint arXiv:1806.02891"},{"key":"2021090816495180100_bib133","article-title":"Reinforcement and imitation learning for diverse visuomotor skills","author":"Zhu","year":"2018","journal-title":"arXiv preprint arXiv:1802.09564"},{"key":"2021090816495180100_bib134","doi-asserted-by":"crossref","first-page":"566","DOI":"10.32470\/CCN.2019.1393-0","article-title":"Self-supervised neural network models of higher visual cortex development","volume-title":"2019 Conference on Cognitive Computational Neuroscience","author":"Zhuang","year":"2019"},{"key":"2021090816495180100_bib135","first-page":"6002","article-title":"Local aggregation for unsupervised learning of visual embeddings","volume-title":"Proceedings of the IEEE International Conference on Computer Vision","author":"Zhuang","year":"2019"}],"container-title":["Journal of Cognitive Neuroscience"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/direct.mit.edu\/jocn\/article-pdf\/33\/10\/2017\/1962083\/jocn_a_01544.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/direct.mit.edu\/jocn\/article-pdf\/33\/10\/2017\/1962083\/jocn_a_01544.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,8]],"date-time":"2021-09-08T19:12:14Z","timestamp":1631128334000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/jocn\/article\/33\/10\/2017\/97402\/Convolutional-Neural-Networks-as-a-Model-of-the"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,1]]},"references-count":135,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2021,9,1]]},"published-print":{"date-parts":[[2021,9,1]]}},"URL":"https:\/\/doi.org\/10.1162\/jocn_a_01544","relation":{},"ISSN":["0898-929X","1530-8898"],"issn-type":[{"value":"0898-929X","type":"print"},{"value":"1530-8898","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,10]]},"published":{"date-parts":[[2021,9,1]]}}}