Publication

Export 136 results:
Filters: Author is Tomaso Poggio  [Clear All Filters]
2021
Adler, A., Araya-Polo, M. & Poggio, T. Deep Learning for Seismic Inverse Problems: Toward the Acceleration of Geophysical Analysis Workflows. IEEE Signal Processing Magazine 38, 89 - 119 (2021).
Banburski, A., De La Torre, F., Pant, N., Shastri, I. & Poggio, T. Distribution of Classification Margins: Are All Data Equal?. (2021).PDF icon CBMM Memo 115.pdf (9.56 MB)PDF icon arXiv version (23.05 MB)
Xu, M. et al. Dynamics and Neural Collapse in Deep Classifiers trained with the Square Loss. (2021).PDF icon JMLR__2021-22.pdf (4.61 MB)PDF icon Small edits (22.65 MB)
Kunhardt, O., Deza, A. & Poggio, T. The Effects of Image Distribution and Task on Adversarial Robustness. (2021).PDF icon CBMM_Memo_116.pdf (5.44 MB)
Gant, J., Banburski, A., Deza, A. & Poggio, T. Evaluating the Adversarial Robustness of a Foveated Texture Transform Module in a CNN. NeurIPS 2021 (2021). at <https://nips.cc/Conferences/2021/Schedule?showEvent=21868>
Poggio, T. From Associative Memories to Powerful Machines. (2021).PDF icon CBMM-Memo-114.pdf (1.01 MB)PDF icon The appendix is now a set of old and new remarks on topics that are not always related to the memo. (3.88 MB)PDF icon Section added on July 24 about theory framework for deep nets (3.88 MB)PDF icon Section added August 6 on self attention (3.9 MB)
Poggio, T. From Marr’s Vision to the Problem of Human Intelligence. (2021).PDF icon CBMM-Memo-118.pdf (362.19 KB)
2020
Mhaskar, H. & Poggio, T. An analysis of training and generalization errors in shallow and deep networks. Neural Networks 121, 229 - 241 (2020).
Reddy, M. Vuyyuru, Banburski, A., Pant, N. & Poggio, T. Biologically Inspired Mechanisms for Adversarial Robustness. (2020).PDF icon CBMM_Memo_110.pdf (3.14 MB)
Poggio, T., Liao, Q. & Banburski, A. Complexity Control by Gradient Descent in Deep Networks. Nature Communications 11, (2020).PDF icon s41467-020-14663-9.pdf (431.68 KB)
Malkin, E., Deza, A. & Poggio, T. CUDA-Optimized real-time rendering of a Foveated Visual System. Shared Visual Representations in Human and Machine Intelligence (SVRHM) workshop at NeurIPS 2020 (2020). at <https://arxiv.org/abs/2012.08655>PDF icon Foveated_Drone_SVRHM_2020.pdf (13.44 MB)PDF icon v1 (12/15/2020) (14.7 MB)
Banburski, A. et al. Dreaming with ARC. Learning Meets Combinatorial Algorithms workshop at NeurIPS 2020 (2020).PDF icon CBMM Memo 113.pdf (1019.64 KB)
Poggio, T. & Liao, Q. Explicit regularization and implicit bias in deep network classifiers trained with the square loss. arXiv (2020). at <https://arxiv.org/abs/2101.00072>
Rangamani, A., Rosasco, L. & 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)
Mhaskar, H. & Poggio, T. Function approximation by deep networks. Communications on Pure & Applied Analysis 19, 4085 - 4095 (2020).PDF icon 1534-0392_2020_8_4085.pdf (514.57 KB)
Deza, A., Liao, Q., Banburski, A. & Poggio, T. Hierarchically Local Tasks and Deep Convolutional Networks. (2020).PDF icon CBMM_Memo_109.pdf (2.12 MB)
Poggio, T., Liao, Q. & Xu, M. Implicit dynamic regularization in deep networks. (2020).PDF icon TPR_ver2.pdf (2.29 MB)PDF icon Substantial edits (1.52 MB)PDF icon Extending theory, setting a post (2 MB)PDF icon Small edits clarifying role of weight decay (2.39 MB)PDF icon Added: prove NC for multiclass+theorem on connected global minima (2.4 MB)PDF icon Update on rank (2.43 MB)
Poggio, T. & 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)
Poggio, T. & Banburski, A. An Overview of Some Issues in the Theory of Deep Networks. IEEJ Transactions on Electrical and Electronic Engineering 15, 1560 - 1571 (2020).
Han, Y., Roig, G., Geiger, G. & Poggio, T. Scale and translation-invariance for novel objects in human vision. Scientific Reports 10, (2020).PDF icon s41598-019-57261-6.pdf (1.46 MB)
Poggio, T. 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)

Pages