All Publications

2020

K. Kar and DiCarlo, J. J., “Fast Recurrent Processing via Ventrolateral Prefrontal Cortex Is Needed by the Primate Ventral Stream for Robust Core Visual Object Recognition”, Neuron, 2020.PDF icon PIIS0896627320307595.pdf (3.92 MB)
CBMM Funded
T. Poggio and Banburski, A., “An Overview of Some Issues in the Theory of Deep Networks”, IEEJ Transactions on Electrical and Electronic Engineering, vol. 15, no. 11, pp. 1560 - 1571, 2020.
CBMM Funded
J. Bill, Pailian, H., Gershman, S. J., and Drugowitsch, J., “Hierarchical structure is employed by humans during visual motion perception”, Proceedings of the National Academy of Sciences, vol. 117, no. 39, pp. 24581 - 24589, 2020.
CBMM Related
CBMM Memo No.
112
T. Poggio, Liao, Q., and Xu, M., “Implicit dynamic regularization in deep networks”. 2020.PDF icon v1.2 (2.29 MB)PDF icon v.59 Update on rank (2.43 MB)
CBMM Funded
H. Mhaskar and Poggio, T., “Function approximation by deep networks”, Communications on Pure & Applied Analysis, vol. 19, no. 8, pp. 4085 - 4095, 2020.PDF icon 1534-0392_2020_8_4085.pdf (514.57 KB)
CBMM Funded
R. Rajalingham, Kar, K., Sanghavi, S., Dehaene, S., and DiCarlo, J. J., “The inferior temporal cortex is a potential cortical precursor of orthographic processing in untrained monkeys”, Nature Communications, vol. 11, no. 1, 2020.PDF icon s41467-020-17714-3.pdf (25.01 MB)
CBMM Funded
CBMM Memo No.
111
S. Madan, Henry, T., Dozier, J., Ho, H., Bhandari, N., Sasaki, T., Durand, F., Pfister, H., and Boix, X., “On the Capability of Neural Networks to Generalize to Unseen Category-Pose Combinations”. 2020.PDF icon CBMM-Memo-111.pdf (9.76 MB)
CBMM Funded
CBMM Memo No.
107
T. Poggio and Cooper, Y., “Loss landscape: SGD has a better view”. 2020.PDF icon CBMM-Memo-107.pdf (1.03 MB)PDF icon Typos and small edits, ver11 (955.08 KB)PDF icon Small edits, corrected Hessian for spurious case (337.19 KB)
CBMM Funded
CBMM Memo No.
110
M. Vuyyuru Reddy, Banburski, A., Pant, N., and Poggio, T., “Biologically Inspired Mechanisms for Adversarial Robustness”. 2020.PDF icon CBMM_Memo_110.pdf (3.14 MB)
CBMM Funded
CBMM Memo No.
109
A. Deza, Liao, Q., Banburski, A., and Poggio, T., “Hierarchically Local Tasks and Deep Convolutional Networks”. 2020.PDF icon CBMM_Memo_109.pdf (2.12 MB)
CBMM Funded
CBMM Memo No.
108
A. Rangamani, Rosasco, L., and Poggio, T., “For interpolating kernel machines, the minimum norm ERM solution is the most stable”. 2020.PDF icon CBMM_Memo_108.pdf (1015.14 KB)PDF icon Better bound (without inequalities!) (1.03 MB)
CBMM Funded
CBMM Memo No.
105
K. M. Villalobos, Štih, V., Ahmadinejad, A., Sundaram, S., Dozier, J., Francl, A., Azevedo, F., Sasaki, T., and Boix, X., “Do Neural Networks for Segmentation Understand Insideness?”. 2020.PDF icon CBMM-Memo-105.pdf (4.63 MB)PDF icon CBMM Memo 105 v2 (July 2, 2020) (3.2 MB)PDF icon CBMM Memo 105 v3 (January 25, 2022) (8.33 MB)
CBMM Funded
W. Lotter, Kreiman, G., and Cox, D., “A neural network trained for prediction mimics diverse features of biological neurons and perception”, Nature Machine Intelligence, vol. 2, no. 4, pp. 210 - 219, 2020.
CBMM Funded
CBMM Memo No.
103
T. Poggio, “Stable Foundations for Learning: a framework for learning theory (in both the classical and modern regime).”. 2020.PDF icon Original file (584.54 KB)PDF icon Corrected typos and details of "equivalence" CV stability and expected error for interpolating machines. Added Appendix on SGD.  (905.29 KB)PDF icon Edited Appendix on SGD. (909.19 KB)PDF icon Deleted Appendix. Corrected typos etc (880.27 KB)PDF icon Added result about square loss and min norm (898.03 KB)
CBMM Funded
K. Kar and DiCarlo, J. J., “Evidence that recurrent pathways between the prefrontal and inferior temporal cortex is critical during core object recognition ”, in COSYNE, Denver, Colorado, USA, 2020.
CBMM Funded
T. Marques, Schrimpf, M., and DiCarlo, J. J., “Hierarchical neural network models that more closely match primary visual cortex tend to better explain higher level visual cortical responses ”, in COSYNE, Denver, Colorado, USA, 2020.
CBMM Funded
T. Poggio, Liao, Q., and Banburski, A., “Complexity Control by Gradient Descent in Deep Networks”, Nature Communications, vol. 11, 2020.PDF icon s41467-020-14663-9.pdf (431.68 KB)
CBMM Funded
M. Schrimpf, Sato, F., Sanghavi, S., and DiCarlo, J. J., “Temporal information for action recognition only needs to be integrated at a choice level in neural networks and primates ”, in COSYNE, Denver, CO, USA, 2020.
CBMM Funded
Y. Han, Roig, G., Geiger, G., and Poggio, T., “Scale and translation-invariance for novel objects in human vision”, Scientific Reports, vol. 10, no. 1411, 2020.PDF icon s41598-019-57261-6.pdf (1.46 MB)
CBMM Funded
H. Mhaskar and Poggio, T., “An analysis of training and generalization errors in shallow and deep networks”, Neural Networks, vol. 121, pp. 229 - 241, 2020.
CBMM Funded

2019

K. M. Jozwik, Lee, M., Marques, T., Schrimpf, M., and Bashivan, P., “Large-scale hyperparameter search for predicting human brain responses in the Algonauts challenge”, in The Algonauts Project: Explaining the Human Visual Brain Workshop 2019 , MIT, Cambridge MA, 2019.
CBMM Funded
CBMM Memo No.
102
T. Poggio, Kur, G., and Banburski, A., “Double descent in the condition number”. 2019.PDF icon Fixing typos, clarifying error in y, best approach is crossvalidation (837.18 KB)PDF icon Incorporated footnote in text plus other edits (854.05 KB)PDF icon Deleted previous discussion on kernel regression and deep nets: it will appear, extended, in a separate paper (795.28 KB)PDF icon correcting a bad typo (261.24 KB)PDF icon Deleted plot of condition number of kernel matrix: we cannot get a double descent curve  (769.32 KB)
CBMM Funded
W. Młynarski and McDermott, J. H., “Ecological origins of perceptual grouping principles in the auditory system”, Proceedings of the National Academy of Sciences, vol. 116, no. 50, pp. 25355 - 25364, 2019.
CBMM Funded
R. McWalter and McDermott, J. H., “Illusory sound texture reveals multi-second statistical completion in auditory scene analysis”, Nature Communications, vol. 10, no. 1, 2019.
CBMM Related
N. Muecke, Neu, G., and Rosasco, L., “Beating SGD Saturation with Tail-Averaging and Minibatching”, Neural Information Processing Systems (NeurIPS 2019). Vancouver, Canada, 2019.PDF icon 9422-beating-sgd-saturation-with-tail-averaging-and-minibatching.pdf (389.35 KB)
CBMM Funded

Pages