All Publications
2017
CBMM Memo No.
071
“Theory of Intelligence with Forgetting: Mathematical Theorems Explaining Human Universal Forgetting using “Forgetting Neural Networks””. 2017. CBMM-Memo-071.pdf (2.54 MB) ,
CBMM Funded
“Self-supervised intrinsic image decomposition.”, in Annual Conference on Neural Information Processing Systems (NIPS), Long Beach, CA, 2017. intrinsicImg_nips_2017.pdf (5.87 MB) ,
CBMM Funded
“A fast, invariant representation for human action in the visual system.”, J Neurophysiol, p. jn.00642.2017, 2017. Author's last draft (695.63 KB) ,
CBMM Funded
“Fisher-Rao Metric, Geometry, and Complexity of Neural Networks”, 2017. 1711.01530.pdf (966.99 KB) ,
CBMM Related
CBMM Funded
CBMM Memo No.
070
“Object-Oriented Deep Learning”. 2017. CBMM-Memo-070.pdf (963.54 KB) ,
CBMM Funded
“Formalizing emotion concepts within a Bayesian model of theory of mind”, Current Option in Psychology, vol. 17, pp. 15-21, 2017. 1-s2.0-S2352250X17300283-main.pdf (613.77 KB) ,
CBMM Funded
CBMM Memo No.
078
“Detecting Semantic Parts on Partially Occluded Objects”. 2017. CBMM-Memo-078.pdf (1.74 MB) ,
CBMM Funded
“Why does deep and cheap learning work so well?”, Journal of Statistical Physics, vol. 168, no. 6, pp. 1223–1247, 2017. 1608.08225.pdf (2.14 MB) ,
CBMM Related
“Mind Games: Game Engines as an Architecture for Intuitive Physics”, Trends in Cognitive Science, vol. 21, no. 9, pp. 649 - 665, 2017. Preprint submitted to Trends in Cognitive Science (17.64 MB) ,
CBMM Funded
“Tunable Efficient Unitary Neural Networks (EUNN) and their application to RNN”, 34th International Conference on Machine Learning, vol. 70. pp. 1733-1741 , 2017. 1612.05231.pdf (2.3 MB) ,
CBMM Related
“Pruning Convolutional Neural Networks for Image Instance Retrieval”, 2017. 1707.05455.pdf (143.46 KB) ,
CBMM Related
CBMM Memo No.
069
“Do Deep Neural Networks Suffer from Crowding?”. 2017. CBMM-Memo-069.pdf (6.47 MB) ,
CBMM Funded
CBMM Memo No.
068
“On the Forgetting of College Academics: at "Ebbinghaus Speed"?”. 2017. CBMM Memo 068-On Forgetting - June 18th 2017 v2.pdf (713.7 KB) ,
CBMM Funded
CBMM Funded
CBMM Memo No.
067
“Musings on Deep Learning: Properties of SGD”. 2017. CBMM Memo 067 v2 (revised 7/19/2017) (5.88 MB) CBMM Memo 067 v3 (revised 9/15/2017) (5.89 MB) CBMM Memo 067 v4 (revised 12/26/2017) (5.57 MB) ,
CBMM Funded
CBMM Memo No.
066
“Theory II: Landscape of the Empirical Risk in Deep Learning”. 2017. CBMM Memo 066_1703.09833v2.pdf (5.56 MB) ,
CBMM Funded
CBMM Memo No.
062
“Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets”. 2017. CBMM-Memo-062.pdf (9.37 MB) ,
CBMM Funded
“Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review”, International Journal of Automation and Computing, pp. 1-17, 2017. art%3A10.1007%2Fs11633-017-1054-2.pdf (1.68 MB) ,
CBMM Funded
“Compression of Deep Neural Networks for Image Instance Retrieval”, 2017. 1701.04923.pdf (614.33 KB) ,
CBMM Related
“View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric Neural Tuning to Head Orientation”, Current Biology, vol. 27, pp. 1-6, 2017. ,
CBMM Funded
“Eccentricity Dependent Deep Neural Networks: Modeling Invariance in Human Vision”, in AAAI Spring Symposium Series, Science of Intelligence, 2017. paper.pdf (963.87 KB) ,
CBMM Funded
“Design of the Artificial: lessons from the biological roots of general intelligence”, 2017. DesignArtificial_Dehghani_arXiv.pdf (222.47 KB) ,
CBMM Related
“Active Video Summarization: Customized Summaries via On-line Interaction.”, in AAAI Conference on Artificial Intelligence, 2017. 21-Garcia-del-Molino-14856.pdf (413.77 KB) ,
CBMM Related