All Publications
2018
CBMM Memo No.
093
“Single units in a deep neural network functionally correspond with neurons in the brain: preliminary results”. 2018. CBMM-Memo-093.pdf (2.99 MB) ,
CBMM Funded
“The Language of Fake News: Opening the Black-Box of Deep Learning Based Detectors”, in workshop on "AI for Social Good", NIPS 2018, Montreal, Canada, 2018. fake-news-paper-NIPS.pdf (147.36 KB) fake-news-paper-NIPS_2018_v2.pdf (147.36 KB) ,
CBMM Funded
“Invariant Recognition Shapes Neural Representations of Visual Input”, Annual Review of Vision Science, vol. 4, no. 1, pp. 403 - 422, 2018. annurev-vision-091517-034103.pdf (1.55 MB) ,
CBMM Funded
“Lucky or clever? From changed expectations to attributions of responsibility”, Cognition, 2018. ,
CBMM Funded
CBMM Memo No.
091
“Classical generalization bounds are surprisingly tight for Deep Networks”. 2018. CBMM-Memo-091.pdf (1.43 MB) CBMM-Memo-091-v2.pdf (1.88 MB) ,
CBMM Funded
CBMM Memo No.
090
“Theory III: Dynamics and Generalization in Deep Networks”. 2018. Original, intermediate versions are available under request (2.67 MB) CBMM Memo 90 v12.pdf (4.74 MB) Theory_III_ver44.pdf Update Hessian (4.12 MB) Theory_III_ver48 (Updated discussion of convergence to max margin) (2.56 MB) fixing errors and sharpening some proofs (2.45 MB) ,
CBMM Funded
CBMM Memo No.
084
“Single-Shot Object Detection with Enriched Semantics”. 2018. CBMM-Memo-084.pdf (1.92 MB) ,
CBMM Funded
CBMM Memo No.
083
“DeepVoting: A Robust and Explainable Deep Network for Semantic Part Detection under Partial Occlusion”. 2018. CBMM-Memo-083.pdf (2.32 MB) ,
CBMM Funded
“Image interpretation above and below the object level”, Proceedings of the Royal Society: Interface Focus, 2018. 2018-BenYosef_Ullman-Image_interpretation_above_and_below the object_level.pdf (3.26 MB) ,
CBMM Funded
“Relational inductive bias for physical construction in humans and machines”, In Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci 2018). 2018. 1806.01203.pdf (1022.51 KB) ,
CBMM Related
CBMM Memo No.
077
“Constant Modulus Algorithms via Low-Rank Approximation”. 2018. CBMM-Memo-077.pdf (795.61 KB) ,
CBMM Funded
“Discovery and usage of joint attention in images”, arXiv.org, 2018. 1804.04604v1.pdf (488.85 KB) ,
CBMM Funded
CBMM Memo No.
076
“An analysis of training and generalization errors in shallow and deep networks”. 2018. CBMM-Memo-076.pdf (772.61 KB) CBMM-Memo-076v2.pdf (2.67 MB) ,
CBMM Funded
“Deep-learning tomography”, The Leading Edge, vol. 37, no. 1, pp. 58 - 66, 2018. TLE2018.pdf (1.9 MB) ,
CBMM Funded
“Brain-Observatory-Toolbox”. 2018. ,
CBMM Funded
“End-to-end differentiable physics for learning and control”, Advances in Neural Information Processing Systems 31 (NIPS 2018). 2018. 7948-end-to-end-differentiable-physics-for-learning-and-control.pdf (794.17 KB) ,
“A computational perspective of the role of Thalamus in cognition”, arxiv, 2018. ThalamusComputationArxiv.pdf (5.12 MB) ,
CBMM Related
“A fast, invariant representation for human action in the visual system”, Journal of Neurophysiology, 2018. ,
CBMM Funded
“MEG action recognition data”. 2018. ,
CBMM Funded
“Theory I: Deep networks and the curse of dimensionality”, Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 66, no. 6, 2018. 02_761-774_00966_Bpast.No_.66-6_28.12.18_K1.pdf (1.18 MB) ,
CBMM Funded
“Theory II: Deep learning and optimization”, Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 66, no. 6, 2018. 03_775-788_00920_Bpast.No_.66-6_31.12.18_K2.pdf (5.43 MB) ,
CBMM Funded
2017
“Building machines that learn and think like people.”, Behavioral and Brain Sciences, vol. 40, p. e253, 2017. ,
CBMM Funded
“Compositional inductive biases in function learning.”, Cogn Psychol, vol. 99, pp. 44-79, 2017. ,
CBMM Funded
CBMM Memo No.
073
“Theory of Deep Learning III: explaining the non-overfitting puzzle”. 2017. CBMM-Memo-073.pdf (2.65 MB) CBMM Memo 073 v2 (revised 1/15/2018) (2.81 MB) CBMM Memo 073 v3 (revised 1/30/2018) (2.72 MB) CBMM Memo 073 v4 (revised 12/30/2018) (575.72 KB) ,
CBMM Funded
CBMM Memo No.
072
“Theory of Deep Learning IIb: Optimization Properties of SGD”. 2017. CBMM-Memo-072.pdf (3.66 MB) ,
CBMM Funded