Skip to content

Latest commit

 

History

History
453 lines (291 loc) · 27.5 KB

dnnsvshuman.md

File metadata and controls

453 lines (291 loc) · 27.5 KB

DNNs vs. Human intelligence

List of articles comparing deep neural networks (DNNs) to human intelligence.

This list is fully up to date (but surely not complete!) until 2018/06, afterwards likely more incomplete

DNN vs. Human Reviews / Commentaries (sorted by year):

Kriegeskorte, N. (2015) – Deep neural networks: a new framework for modeling biological vision and brain information processing. Annual review of vision science, 1, 417-446. https://doi.org/10.1146/annurev-vision-082114-035447

Gauthier, I., & Tarr, M. J. (2016). Visual object recognition: Do we (finally) know more now than we did? Annual review of vision science, 2, 377-396. https://doi.org/10.1146/annurev-vision-111815-114621

Marblestone, A. H., Wayne, G., & Kording, K. P. (2016). Toward an integration of deep learning and neuroscience. Frontiers in Computational Neuroscience, 10, 94. https://doi.org/10.3389/fncom.2016.00094 Excellent, very complete review of the ML/cortex frontier. It argues in favour of a computational neuroscience that researches the brain’s cost functions and their optimisation processes, rather than specific circuits. It debates what ML can learn from neuroscience and vice-versa.

Yamins, D. L., & DiCarlo, J. J. (2016). Using goal-driven deep learning models to understand sensory cortex. Nature neuroscience, 19(3), 356 https://doi.org/10.1038/nn.4244 Gentle introduction to Convolutional Neural Networks and their use for predicting the encoding strategy of sensory areas. Mostly conversational, does not present hard analytical or data-driven results other than as a review.

Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017). Neuroscience-inspired artificial intelligence. Neuron, 95(2), 245-258. https://doi.org/10.1016/j.neuron.2017.06.011 General view, including historical perspective, of AI/Neuroscience relationships. Particularly focused on the cognitive/behavioural level (transfer learning, reinforcement learning, attention, memory). By DeepMind founder Demis Hassabis and colleagues.

Kay, K. N. (2017). Principles for models of neural information processing. NeuroImage. http://dx.doi.org/10.1016/j.neuroimage.2017.08.016

Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2017). Building machines that learn and think like people. Behavioral and Brain Sciences, 40. https://doi.org/10.1017/S0140525X16001837 VanRullen, R. (2017). Perception science in the age of deep neural networks. Frontiers in psychology, 8, 142. https://doi.org/10.3389/fpsyg.2017.00142

Aru, J., & Vicente, R. (2018). What deep learning can tell us about higher cognitive functions like mindreading?. arXiv preprint arXiv:1803.10470. https://arxiv.org/abs/1803.10470

Barrett, David GT, Ari S. Morcos, and Jakob H. Macke. 'Analyzing biological and artificial neural networks: challenges with opportunities for synergy?.' arXiv preprint arXiv:1810.13373 (2018). https://arxiv.org/abs/1810.13373 Good overview on challenges and opportunities in comparing DNNs with BioNets. What analysis methods can be used on both? What methods can be used to compare them to each other?

Glaser, J. I., Benjamin, A. S., Farhoodi, R., & Kording, K. P. (2018). The Roles of Supervised Machine Learning in Systems Neuroscience. arXiv preprint arXiv:1805.08239. https://arxiv.org/abs/1805.08239 How can machine learning be used in neuroscience? 1. Solving engineering problems; 2. Identifying predictive variables; 3. Benchmarking simple models; 4. Serving as a model for the brain.

Majaj, N. J., & Pelli, D. G. (2018). Deep learning—Using machine learning to study biological vision. Journal of vision, 18(13), 2-2 https://doi.org/10.1167/18.13.2

Cichy, R. M., Kaiser, D. (2019). Deep neural networks as scientific models. Trends in Cognitive Sciences. https://doi.org/10.1016/j.tics.2019.01.009

Kietzmann, T. C., McClure, P., & Kriegeskorte, N. (2019). Deep neural networks in computational neuroscience. In Oxford Research Encyclopedia of Neuroscience. Oxford University Press. doi: http://dx.doi.org/10.1093/acrefore/9780190264086.013.46 http://oxfordre.com/neuroscience/view/10.1093/acrefore/9780190264086.001.0001/acrefore-9780190264086-e-46

Storrs, K. & Kriegeskorte, N. (2019). Deep Learning for Cognitive Neuroscience. In The Cognitive Neurosciences, 6th Edition. https://arxiv.org/abs/1903.01458

Learning in DNN vs. Brain; Bio-plausible learning (reviews)

Marblestone et al. (2016). Toward an integration of deep learning and neuroscience. See above.

Whittington and Bogacz, Theories of Error Back-propagation in the Brain, Trends in Cog Sci 2018 https://www.cell.com/trends/cognitive-sciences/fulltext/S1364-6613(19)30012-9 A review with a particular focus on bio-plausible implementations of backpropagation in artificial neural networks.

Pieter R. Roelfsema & Anthony Holtmaat, Control of synaptic plasticity in deep cortical networks, Nat Rev Neurosci 19, 166–180 (2018) https://www.nature.com/articles/nrn.2018.6 Bio-oriented. Neuroscience review on how the brain may solve the “credit assignment problem” by means of neuromodulation and feedback that “gate” and “steer” plasticity in earlier layers, based on the outcome of the action and on what synapses contributed to the decision.

DNN vs. Brain Imaging Papers (sorted by year and alphabetically):

Please no medical imaging papers!

2014

Cadieu et al (2014) – Deep Neural Networks Rival the Representation of Primate IT Cortex for Core Visual Object Recognition – PloS Comput Biol https://doi.org/10.1371/journal.pcbi.1003963

Khaligh-Razavi & Kriegeskorte (2014) – Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation – PloS Comput Biol https://doi.org/10.1371/journal.pcbi.1003915

Yamins et al (2014) – Performance-optimized hierarchical models predict neural responses in higher visual cortex – PNAS http://www.pnas.org/content/111/23/8619.short

2015

Güçlü & van Gerven (2015) – Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream – J Neurosci https://doi.org/10.1523/JNEUROSCI.5023-14.2015

Güçlü & van Gerven (2015) – Increasingly complex representations of natural movies across the dorsal stream are shared between subjects – Neuroimage https://doi.org/10.1016/j.neuroimage.2015.12.036

2016

Cichy et al (2016) - Comparison of deep neural networks to spatio-temporal cortical dynamics of human visual object recognition reveals hierarchical correspondence – Sci Reports https://www.nature.com/articles/srep27755

Güçlü et al (2016) – Brains on beats – NIPS https://papers.nips.cc/paper/6222-brains-on-beats.pdf

Hong et al (2016) – Explicit information for category-orthogonal object properties increases along the ventral stream – Nature Neuroscience https://www.nature.com/articles/nn.4247

Yamins & DiCarlo (2016) – Using goal-driven deep learning models to understand sensory cortex – Nature Neuroscience https://www.nature.com/articles/nn.4244

2017

Cichy et al (2017) – Dynamics of scene representations in the human brain revealed by magnetoencephalography and deep neural networks – Neuroimage https://doi.org/10.1016/j.neuroimage.2016.03.063

Eickenberg et al (2017) – Seeing it all: Convolutional network layers map the function of the human visual system – Neuroimage https://doi.org/10.1016/j.neuroimage.2016.10.001

Güçlütürk, Güçlü, Seeliger, Bosch, van Lier, van Gerven (2017) – Reconstructing perceived faces from brain activations with deep adversarial neural decoding – NIPS http://papers.nips.cc/paper/7012-reconstructing-perceived-faces-from-brain-activations-with-deep-adversarial-neural-decoding.pdf

Güçlü & van Gerven (2017) – Modeling the Dynamics of Human Brain Activity with Recurrent Neural Networks – Front Comput Neurosci https://dx.doi.org/10.3389%2Ffncom.2017.00007

Horikawa & Kamitani (2017) – Hierarchical neural representation of dreamed objects revealed by brain decoding with deep neural network features – Front Comput Neurosci https://doi.org/10.3389/fncom.2017.00004

Horikawa & Kamitani (2017) – Generic decoding of seen and imagined objects using hierarchical visual features – Nat Commun https://dx.doi.org/10.1038%2Fncomms15037

Kalfas, Kumar, Vogels (2017) – Shape Selectivity of Middle Superior Temporal Sulcus Body Patch Neurons – eNeuro https://doi.org/10.1523/ENEURO.0113-17.2017

Karimi-Rouzbahani et al (2017) - Hard-wired feed-forward visual mechanisms of the brain compensate for affine variations in object recognition - Journal of Neuroscience https://doi.org/10.1016/j.neuroscience.2017.02.050

Khaligh-Razavi et al (2017) – Fixed versus mixed RSA: Explaining visual representations by fixed and mixed feature sets from shallow and deep computational models – J Math Psych https://doi.org/10.1016/j.jmp.2016.10.007

Klindt, Ecker, Euler, Bethge (2017) – Neural system identification for large populations separating “what” and “where” – NIPS http://papers.nips.cc/paper/6942-neural-system-identification-for-large-populations-separating-what-and-where

Ratan Murty & Arun (2017) – A balanced comparison of object invariances in monkey IT neurons – eNeuro https://doi.org/10.1523/ENEURO.0333-16.2017

Scholte et al (2017) - Visual pathways from the perspective of cost functions and multi-task deep neural networks - Cortex https://doi.org/10.1016/j.cortex.2017.09.019

Seeliger et al (2017) – Convolutional neural network-based encoding and decoding of visual object recognition in space and time – Neuroimage https://doi.org/10.1016/j.neuroimage.2017.07.018

Seeliger et al (2017) - Generative adversarial networks for reconstructing natural images from brain activity. NeuroImage 181 http://www.sciencedirect.com/science/article/pii/S105381191830658X (preprint: https://doi.org/10.1101/226688 )

Tacchetti, Isik, Poggio (2017) – Invariant recognition drives neural representations of action sequences – PloS Comput Biology https://doi.org/10.1371/journal.pcbi.1005859

Tripp et al (2017) – Similarities and differences between stimulus tuning in the inferotemporal visual cortex and convolutional networks - IJCNN https://arxiv.org/abs/1612.06975

Wen et al (2017) – Neural Encoding and Decoding with Deep Learning for Dynamic Natural Vision – Cerebral Cortex https://doi.org/10.1093/cercor/bhx268

Zhuang, Wang, Yamins, Hu (2017) – Deep learning predicts correlation between a functional signature of higher visual areas and sparse firing of neurons – Front Comput Neurosci https://doi.org/10.3389/fncom.2017.00100

2018

Abdelhack, Kamitani (2018) – Sharpening of hierarchical visual feature representations of blurred images – eNeuro https://doi.org/10.1523/ENEURO.0443-17.2018

Bankson, Hebart, Groen, Baker (2018) – The temporal evolution of conceptual object representations revealed through models of behavior, semantics and deep neural networks – Neuroimage https://doi.org/10.1016/j.neuroimage.2018.05.037

Banino et al (2018) - Vector-based navigation using grid-like representations in artificial agents - Nature https://doi.org/10.1038/s41586-018-0102-6

Bonner, Epstein (2018) – Computational mechanisms underlying cortical responses to the affordance properties of visual scenes – PloS Computational Biology https://doi.org/10.1371/journal.pcbi.1006111

Devereaux, Clarke, Tyler (2018) - Integrated deep visual and semantic attractor neural networks predict fMRI pattern-information along the ventral object processing pathway - Scientific Reports https://doi.org/10.1038/s41598-018-28865-1

Fong, Scheirer, Cox (2018) - Using human brain activity to guide machine learning - Scientific Reports https://doi.org/10.1038/s41598-018-23618-6

Greene & Hansen (2018) - Shared spatiotemporal category representations in biological and artificial deep neural networks - PloS Comput Biol https://doi.org/10.1371/journal.pcbi.1006327

Groen et al (2018) – Distinct contributions of functional and deep neural network features to scene representation in brain and behavior – eLife https://doi.org/10.7554/eLife.32962

Kell, Yamins, Shook, Norman-Haignere, McDermott (2018) – A task-optimized neural network replicates human auditory behavior, predicts brain responses, and reveals a cortical processing hierarchy – Neuron https://doi.org/10.1016/j.neuron.2018.03.044

O’Connell and Chun (2018) – Predicting eye movements from fMRI responses to natural scenes – Nature Communications https://doi.org/10.1038/s41467-018-07471-9

Rajalingham et al (2018): Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks. Journal of Neuroscience 38. (preprint: http://dx.doi.org/10.1101/240614 ) http://www.jneurosci.org/content/38/33/7255

Ratan Murty, Arun (2018) – Multiplicative mixing of object identity and image attributes in single inferior temporal neurons – PNAS https://doi.org/10.1073/pnas.1714287115

Shi et al (2018) – Deep recurrent neural network reveals a hierarchy of process memory during dynamic natural vision – Human Brain Mapping http://dx.doi.org/10.1002/hbm.24006

Tang, Schrimpf, Lotter, Moerman, Paredes, Caro, Hardesty, Cox, and Kreiman (2018) – Recurrent computations for visual pattern completion – PNAS https://doi.org/10.1073/pnas.1719397115

Wen et al (2018) – Deep Residual Network Reveals a Nested Hierarchy of Distributed Cortical Representation for Visual Categorization – Scientific Reports https://www.nature.com/articles/s41598-018-22160-9

Wenliang, Seitz (2018) - Deep neural networks for modeling visual perceptual learning - J Neurosci https://doi.org/10.1523/JNEUROSCI.1620-17.2018

2019

Kar, Kubilius, Schmidt, Issa, DiCarlo (2018) - Evidence that recurrent circuits are critical to the ventral stream's execution of core object recognition behavior - Nature Neuroscience https://doi.org/10.1038/s41593-019-0392-5 Preprint: https://doi.org/10.1101/354753

Preprints

Agrawal et al (2014) - Pixels to Voxels: Modeling Visual Representation in the Human Brain - arXiv https://arxiv.org/pdf/1407.5104.pdf

Bracci, Kalfas, Op de Beeck (2017) – The ventral visual pathway represents animal appearance over animacy, unlike human behavior and deep neural networks – bioRxiv https://doi.org/10.1101/228932

Bashivan, Kar, DiCarlo (2018) - Neural population control via deep image synthesis - bioRxiv https://doi.org/10.1101/461525

Cadena et al (2017) - Deep convolutional models improve predictions of macaque V1 responses to natural images - bioRxiv https://doi.org/10.1101/201764

Cichy et al (2017) - Neural dynamics of real-world object vision that guide behaviour - bioRxiv https://www.biorxiv.org/content/early/2017/06/08/147298

Devereux, Clarke, Tyler (2018) – Integrated deep visual and semantic attractor neural networks predict fMRI pattern-information along the ventral object processing pathway – bioRxiv https://doi.org/10.1101/302406

Dwivedi, Roig (2018) - Task-specific vision models explain task-specific areas of visual cortex - bioRxiv https://www.biorxiv.org/content/early/2018/08/28/402735

Gwilliams & King (2017) - Performance-optimized hierarchical models only partially predict neural responses during perceptual decision making - bioRxiv https://www.biorxiv.org/content/early/2017/11/20/221630.full

King, Groen, Steel, Kravitz, Baker (2018) - Similarity judgments and cortical visual responses reflect different properties of object and scene categories in naturalistic images – bioRxiv https://doi.org/10.1101/316554

Kindel, Christensen, Zylberberg (2017) – Using deep learning to reveal the neural code for images in primary visual cortex – arxiV https://arxiv.org/abs/1706.06208

Kuzovkin et al (2017) - Activations of Deep Convolutional Neural Network are Aligned with Gamma Band Activity of Human Visual Cortex - BioRxiv https://doi.org/10.1101/133694

Long et al (2017) - A mid-level organization of the ventral stream - BioRXiv https://doi.org/10.1101/213934

Lotter, Kreiman, Cox (2018) – A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception – arXiv https://arxiv.org/abs/1805.10734

Nayebi, Bear, Kubilius, Kar, Ganguli, Sussillo, DiCarlo, Yamins (2018) - Task-Driven Convolutional Recurrent Models of the Visual System - arXiv https://arxiv.org/abs/1807.00053

O’Connell & Chun (2017) - Predicting eye movements with deep neural network activity decoded from fMRI responses to natural scenes - bioRxiv https://doi.org/10.1101/166421

Pinotsis, Siegel, Miller (2019) - Sensory processing and categorization in cortical and deep neural networks - bioRxiv https://doi.org/10.1101/647222

Ponce, Xiao, Schade, Hartmann, Kreiman, Livingstone (2019) - Evolving super stimuli for real neurons using deep generative networks - bioRxiv doi: https://doi.org/10.1101/516484

Qiao, Zhang, Wang, Yan, Chen, Zeng, Tong (2018) – Accurate reconstruction of image stimuli from human fMRI based on the decoding model with capsule network architecture – arXiv https://arxiv.org/abs/1801.00602

Rajaei, Mohsenzadeh, Ebrahimpour, Khaligh-Razavi (2018) – Beyond core object recognition: Recurrent processes account for object recognition under occlusion – bioRxiv https://doi.org/10.1101/302034

Ramakrishnan et al (2017) - Characterizing the temporal dynamics of object recognition by deep neural networks: role of depth - bioRxiv https://doi.org/10.1101/178541

Shen, G., Horikawa, T., Majima, K., & Kamitani, Y. (2017). Deep image reconstruction from human brain activity - bioRxiv. https://www.biorxiv.org/content/early/2017/12/28/240317

Tang, Schrimpf, Lotter, et al (2017) - Recurrent computations for visual pattern completion - arXiv https://arxiv.org/abs/1706.02240

VanRullen & Reddy (2018) – Reconstructing faces from fMRI patterns using deep generative neural networks – arXiv https://arxiv.org/abs/1810.03856

Walker, Sinz, Froudarakis, Fahey, Muhammad, Ecker, Cobos, Reimer, Pitkow, & Tolias (2019) - Inception in visual cortex: in vivo-silico loops reveal most exciting images - biorXiv https://doi.org/10.1101/506956

Wen et al (2017) – Transferring and Generalizing Deep-Learning-based Neural Encoding Models across Subjects – bioRxiv https://dxoi.org/10.1101/171017

Zhang, Qiao, Wang, Tong, Zeng, Yan (2018) – Constraint-free natural image reconstruction from fMRI signals based on convolutional neural network – arXiv https://arxiv.org/abs/1801.05151

DNN vs. Behavior Papers (sorted by year and alphabetically):

2014

Ghodrati et al (2014) – Feedforward object-vision models only tolerate small image variations compared to human – Front Comput Neurosci https://dx.doi.org/10.3389%2Ffncom.2014.00074

2015

Lake et al (2015) - Deep neural networks predict category typicality ratings for images - Cogn Psych http://gureckislab.org/papers/LakeZarembaFergusGureckis.CogSci2015.pdf

Nguyen et al (2015) – Deep Neural Networks Are Easily Fooled: High Confidence Predictions for Unrecognizable Images – IEEE Comput Vis Patt Recog https://www.cv-foundation.org/openaccess/content_cvpr_2015/papers/Nguyen_Deep_Neural_Networks_2015_CVPR_paper.pdf

Rajalingham et al (2015) – Comparison of object recognition behavior in human and monkey. Journal of Neuroscience http://www.jneurosci.org/content/35/35/12127

2016

Eberhardt et al (2016) – How deep is the feature analysis underlying rapid visual categorization – NIPS http://papers.nips.cc/paper/6218-how-deep-is-the-feature-analysis-underlying-rapid-visual-categorization

Farzmahdi et al (2016) – A specialized face-processing model inspired by the organization of monkey face patches explains several face-specific phenomena observed in humans – Sci Rep https://dx.doi.org/10.1038%2Fsrep25025

Greene et al (2016) – Visual Scenes Are Categorized by Function – JEP:General http://psycnet.apa.org/fulltext/2015-58122-004.html

Kheradpisheh et al (2016) – Deep Networks Can Resemble Human Feed-forward Vision in Invariant Object Recognition – Sci Rep https://www.nature.com/articles/srep32672

Kheradpisheh et al (2016) – Humans and Deep Networks Largely Agree on Which Kinds of Variation Make Object Recognition Harder – Front Comput Neurosci https://dx.doi.org/10.3389%2Ffncom.2016.00092

Kubilius et al (2016) – Deep Neural Networks as a Computational Model for Human Shape Sensitivity – PloS Comput Biol https://doi.org/10.1371/journal.pcbi.1004896

2017

Jozwik et al (2017) – Deep Convolutional Neural Networks Outperform Feature-Based But Not Categorical Models in Explaining Object Similarity Judgments – Front Psychol https://doi.org/10.3389/fpsyg.2017.01726

Karimi-Rouzbahani, Bagheri & Ebrahimpour (2017) – Invariant object recognition is a personalized selection of invariant features in humans, not simply explained by hierarchical feed-forward vision models – Scientific Reports https://doi.org/10.1038/s41598-017-13756-8

Love et al (2017) – Deep Networks as Models of Human and Animal Categorization - Cogn Psych https://mindmodeling.org/cogsci2017/papers/0283/paper0283.pdf

Lukavský, J., & Děchtěrenko, F. (2017). Visual properties and memorising scenes: Effects of image-space sparseness and uniformity. Attention, Perception, & Psychophysics, 79(7), 2044–2054. https://doi.org/10.3758/s13414-017-1375-9

Song, Yang, Wang (2017) – Reward-based training of recurrent neural networks for cognitive and value-based tasks – eLife https://dx.doi.org/10.7554%2FeLife.21492

Suzuki et al (2017) - A Deep-Dream Virtual Reality Platform for Studying Altered Perceptual Phenomenology - Scientific Reports https://doi.org/10.1038/s41598-017-16316-2

Wallis et al (2017) – A parametric texture model based on deep convolutional features closely matches texture appearance for humans – JoV http://jov.arvojournals.org/article.aspx?articleid=2657215

Wichmann, F. A., Janssen, D. H., Geirhos, R., Aguilar, G., Schütt, H. H., Maertens, M., & Bethge, M. (2017). Methods and measurements to compare men against machines. Electronic Imaging, 2017(14), 36-45. https://doi.org/10.2352/ISSN.2470-1173.2017.14.HVEI-113

Tang, Schrimpf, Lotter, et al (2017) - Recurrent computations for visual pattern completion - arXiv https://arxiv.org/abs/1706.02240

2018

Baker, Lu, Erlikhman, Kellman (2018) – Deep convolutional networks do not classify based on global object shape – PLoS Computational Biology https://doi.org/10.1371/journal.pcbi.1006613

Flesch, Balaguer, Dekker, Nili, & Summerfield (2018) – Comparing continual task learning in minds and machines – PNAS https://doi.org/10.1073/pnas.1803839115

Geirhos, Medina Temme, Rauber, Schütt, Bethge, Wichmann (2018) - Generalisation in humans and deep neural networks - NeurIPS https://arxiv.org/abs/1808.08750

Masse, Grant, & Freedman (2018) – Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization – PNAS https://doi.org/10.1073/pnas.1803839115

Rajalingham et al (2018): Large-Scale, High-Resolution Comparison of the Core Visual Object Recognition Behavior of Humans, Monkeys, and State-of-the-Art Deep Artificial Neural Networks. Journal of Neuroscience 38. (preprint: http://dx.doi.org/10.1101/240614 ) http://www.jneurosci.org/content/38/33/7255

Watanabe et al (2018) - Illusory Motion Reproduced by Deep Neural Networks Trained for Prediction - Frontiers in Psychology https://doi.org/10.3389/fpsyg.2018.00345

Wenliang, Seitz (2018) - Deep neural networks for modeling visual perceptual learning - J Neurosci https://doi.org/10.1523/JNEUROSCI.1620-17.2018

Xu, Garrod, Scholte, Ince, Schyns (2018) - Using Psychophysical Methods to Understand Mechanisms of Face Identification in a Deep Neural Network - CVPRW https://0ceabf3e-a-62cb3a1a-s-sites.googlegroups.com/site/skytianxu/xu2018%20Using%20Psychophysical%20Methods%20to%20Understand%20Mechanisms%20of%20Face%20Identification%20in%20a%20Deep%20Neural%20Network.pdf

2019

Geirhos; Rubisch, Michaelis, Bethge, Wichmann, & Brendel (2018) - ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness ICLR 2019 (Oral) https://openreview.net/forum?id=Bygh9j09KX

Preprints

Peterson et al (2016) – Adapting deep network features to capture psychological representations – ArXiv https://arxiv.org/abs/1608.02164

Battleday, Peterson, Griffiths (2017) – Modeling Human Categorization of Natural Images Using Deep Feature Representations - ArXiv https://arxiv.org/abs/1711.04855

Dekel (2017) - Human perception in computer vision - arXiv https://arxiv.org/abs/1701.04674

Fan, Yamins, & Turk-Browne (2017) – Common object representations for visual production and recognition – bioRxiv https://www.biorxiv.org/content/early/2017/01/03/097840

Geirhos, Janssen, Schütt, Rauber, Bethge, & Wichmann (2017) – Comparing deep neural networks against humans: object recognition when the signal gets weaker – ArXiv https://arxiv.org/abs/1706.06969

Lin et al (2017) – Transfer of view-manifold learning to similarity perception of novel objects – ArXiv https://arxiv.org/abs/1704.00033

Lindsay & Miller (2017) - Understanding Biological Visual Attention Using Convolutional Neural Networks – biorXiv https://www.biorxiv.org/content/early/2017/12/20/233338

Fruend, Stalker (2018) – Measuring human sensitivity to perturbations within the manifold of natural images – bioRxiv https://doi.org/10.1101/320531

Leibo et al (2018) - Psychlab: A Psychology Laboratory for Deep Reinforcement Learning Agents - arXiv https://arxiv.org/abs/1801.08116

Linsley, Scheibler, Eberhardt, Serre (2018) – Global-and-local attention networks for visual recognition – arXiv https://arxiv.org/abs/1805.08819

Hugo Richard, Ana Pinho, Bertrand Thirion, Guillaume Charpiat (2018) – Optimizing deep video representations to match brain activity – arXiv https://arxiv.org/abs/1809.02440

Rosenfeld, Solbach, Tsotsos (2018) – Totally Looks Like - How Humans Compare, Compared to Machines – arXiv https://arxiv.org/abs/1803.01485

Wallis, T. S. A., Funke, C. M., Ecker, A. S., Gatys, L. A., Wichmann, F. A., & Bethge, M. (2018). Image content is more important than Boumas Law for scene metamers. BioRxiv. https://doi.org/10.1101/378521

Fruend, I. Simple, biologically informed models, but not convolutional neural networks describe target detection in naturalistic images. bioRxiv. https://doi.org/10.1101/578633

Kim, B., Reif, E., Wattenberg, M., Bengio, S. (2019). Do neural networks show gestalt phenomena? An exploration of the law of closure. https://arxiv.org/abs/1903.01069

Work using older DNN models (e.g. HMAX)

(everything else, obviously incomplete)

Fukushima, K. (1988). Neocognitron: A hierarchical neural network capable of visual pattern recognition. Neural networks, 1(2), 119-130.

van Gerven, Marcel AJ, Floris P. de Lange, and Tom Heskes (2010). 'Neural decoding with hierarchical generative models.' Neural computation 22.12 (2010): 3127-3142.

Zeman et al (2013) The Müller-Lyer Illusion in a Computational Model of Biological Object Recognition. PLoS ONE8(2): e56126. https://doi.org/10.1371/journal.pone.0056126

Zeman et al (2014) - Complex cells decrease errors for the Müller-Lyer illusion in a model of the visual ventral stream - Front. Comput. Neurosci. 8:112. https://doi.org/10.3389/fncom.2014.00112

Ramakrishnan K, Scholte HS, Groen IIA, Smeulders AWM, Ghebreab S (2015) -Visual dictionaries as intermediate features in the human brain - Front Comput Neurosci https://www.frontiersin.org/articles/10.3389/fncom.2014.00168/full (HMAX vs bag-of-words tested against fMRI)

Tang, Schrimpf, Lotter, et al (2017) - Recurrent computations for visual pattern completion - arXiv https://arxiv.org/abs/1706.02240

Ponce, Lomber, Livingstone (2018) - Posterior Inferotemporal Cortex Cells Use Multiple Input Pathways for Shape Encoding - Journal of Neuroscience http://www.jneurosci.org/content/37/19/5019