Publication
Export 139 results:
Filters: Author is Tomaso Poggio [Clear All Filters]
Feature learning in deep classifiers through Intermediate Neural Collapse. (2023).
Feature_Learning_memo.pdf (2.16 MB)

PCA as a defense against some adversaries. (2022).
CBMM-Memo-135.pdf (2.58 MB)

Representation Learning in Sensory Cortex: a theory. IEEE Access 1 - 1 (2022). doi:10.1109/ACCESS.2022.3208603
Representation_Learning_in_Sensory_Cortex_a_theory.pdf (1.17 MB)

Deep Learning for Seismic Inverse Problems: Toward the Acceleration of Geophysical Analysis Workflows. IEEE Signal Processing Magazine 38, 89 - 119 (2021).
Distribution of Classification Margins: Are All Data Equal?. (2021).
CBMM Memo 115.pdf (9.56 MB)
arXiv version (23.05 MB)


Dynamics and Neural Collapse in Deep Classifiers trained with the Square Loss. (2021).
v1.0 (4.61 MB)
v1.4corrections to generalization section (5.85 MB)
v1.7Small edits (22.65 MB)



The Effects of Image Distribution and Task on Adversarial Robustness. (2021).
CBMM_Memo_116.pdf (5.44 MB)

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>
From Associative Memories to Powerful Machines. (2021).
v1.0 (1.01 MB)
v1.3Section added August 6 on self attention (3.9 MB)


From Marr’s Vision to the Problem of Human Intelligence. (2021).
CBMM-Memo-118.pdf (362.19 KB)

An analysis of training and generalization errors in shallow and deep networks. Neural Networks 121, 229 - 241 (2020).
Biologically Inspired Mechanisms for Adversarial Robustness. (2020).
CBMM_Memo_110.pdf (3.14 MB)

Complexity Control by Gradient Descent in Deep Networks. Nature Communications 11, (2020).
s41467-020-14663-9.pdf (431.68 KB)

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>
Foveated_Drone_SVRHM_2020.pdf (13.44 MB)
v1 (12/15/2020) (14.7 MB)


Dreaming with ARC. Learning Meets Combinatorial Algorithms workshop at NeurIPS 2020 (2020).
CBMM Memo 113.pdf (1019.64 KB)

Explicit regularization and implicit bias in deep network classifiers trained with the square loss. arXiv (2020). at <https://arxiv.org/abs/2101.00072>
For interpolating kernel machines, the minimum norm ERM solution is the most stable. (2020).
CBMM_Memo_108.pdf (1015.14 KB)
Better bound (without inequalities!) (1.03 MB)


Function approximation by deep networks. Communications on Pure & Applied Analysis 19, 4085 - 4095 (2020).
1534-0392_2020_8_4085.pdf (514.57 KB)

Hierarchically Local Tasks and Deep Convolutional Networks. (2020).
CBMM_Memo_109.pdf (2.12 MB)

Implicit dynamic regularization in deep networks. (2020).
v1.2 (2.29 MB)
v.59 Update on rank (2.43 MB)


Loss landscape: SGD has a better view. (2020).
CBMM-Memo-107.pdf (1.03 MB)
Typos and small edits, ver11 (955.08 KB)
Small edits, corrected Hessian for spurious case (337.19 KB)


