Publication
] Double descent in the condition number. (2019).
Fixing typos, clarifying error in y, best approach is crossvalidation (837.18 KB) Incorporated footnote in text plus other edits (854.05 KB) Deleted previous discussion on kernel regression and deep nets: it will appear, extended, in a separate paper (795.28 KB) correcting a bad typo (261.24 KB) Deleted plot of condition number of kernel matrix: we cannot get a double descent curve (769.32 KB)
Fixing typos, clarifying error in y, best approach is crossvalidation (837.18 KB) Incorporated footnote in text plus other edits (854.05 KB) Deleted previous discussion on kernel regression and deep nets: it will appear, extended, in a separate paper (795.28 KB) correcting a bad typo (261.24 KB) Deleted plot of condition number of kernel matrix: we cannot get a double descent curve (769.32 KB) A Perspective: Sparse Compositionality and Efficiently Computable Intelligence. (2026). Perspective_SPCOMP-9.pdf (170.23 KB)
Perspective_SPCOMP-9.pdf (170.23 KB) Deep Learning: mathematics and neuroscience. (2016). Deep Learning- mathematics and neuroscience.pdf (1.25 MB)
Deep Learning- mathematics and neuroscience.pdf (1.25 MB) Compositional sparsity of learnable functions. Bulletin of the American Mathematical Society 61, 438-456 (2024).
On efficiently computable functions, deep networks and sparse compositionality. (2025). Deep_sparse_networks_approximate_efficiently_computable_functions.pdf (223.15 KB)
Deep_sparse_networks_approximate_efficiently_computable_functions.pdf (223.15 KB) Implicit dynamic regularization in deep networks. (2020). v1.2 (2.29 MB) v.59 Update on rank (2.43 MB)
v1.2 (2.29 MB) v.59 Update on rank (2.43 MB) Stable Foundations for Learning: a framework for learning theory (in both the classical and modern regime). (2020). Original file (584.54 KB) Corrected typos and details of "equivalence" CV stability and expected error for interpolating machines. Added Appendix on SGD. (905.29 KB) Edited Appendix on SGD. (909.19 KB) Deleted Appendix. Corrected typos etc (880.27 KB) Added result about square loss and min norm (898.03 KB)
Original file (584.54 KB) Corrected typos and details of "equivalence" CV stability and expected error for interpolating machines. Added Appendix on SGD. (905.29 KB) Edited Appendix on SGD. (909.19 KB) Deleted Appendix. Corrected typos etc (880.27 KB) Added result about square loss and min norm (898.03 KB) Visual Cortex and Deep Networks: Learning Invariant Representations. 136 (The MIT Press, 2016). at <https://mitpress.mit.edu/books/visual-cortex-and-deep-networks>
Deep Leaning: Mathematics and Neuroscience. A Sponsored Supplement to Science Brain-Inspired intelligent robotics: The intersection of robotics and neuroscience, 9-12 (2016).
Complexity Control by Gradient Descent in Deep Networks. Nature Communications 11, (2020). s41467-020-14663-9.pdf (431.68 KB)
s41467-020-14663-9.pdf (431.68 KB) Associative Memory as the Core of Intelligence in Technology and Evolution. (2026). Review_On_Associative_Memories-14.pdf (245.78 KB)
Review_On_Associative_Memories-14.pdf (245.78 KB) Theory II: Landscape of the Empirical Risk in Deep Learning. (2017). CBMM Memo 066_1703.09833v2.pdf (5.56 MB)
CBMM Memo 066_1703.09833v2.pdf (5.56 MB) I-theory on depth vs width: hierarchical function composition. (2015). cbmm_memo_041.pdf (1.18 MB)
cbmm_memo_041.pdf (1.18 MB) From Associative Memories to Powerful Machines. (2021). v1.0 (1.01 MB) v1.3Section added August 6 on self attention (3.9 MB)
v1.0 (1.01 MB) v1.3Section added August 6 on self attention (3.9 MB) Computational role of eccentricity dependent cortical magnification. (2014). CBMM-Memo-017.pdf (1.04 MB)
CBMM-Memo-017.pdf (1.04 MB) Explicit regularization and implicit bias in deep network classifiers trained with the square loss. arXiv (2020). at <https://arxiv.org/abs/2101.00072>
How Deep Sparse Networks Avoid the Curse of Dimensionality: Efficiently Computable Functions are Compositionally Sparse. (2022). v1.0 (984.15 KB) v5.7 adding in context learning etc (1.16 MB)
v1.0 (984.15 KB) v5.7 adding in context learning etc (1.16 MB) Theory II: Deep learning and optimization. Bulletin of the Polish Academy of Sciences: Technical Sciences 66, (2018). 03_775-788_00920_Bpast.No_.66-6_31.12.18_K2.pdf (5.43 MB)
03_775-788_00920_Bpast.No_.66-6_31.12.18_K2.pdf (5.43 MB) Is Research in Intelligence an Existential Risk?. (2014). Is Research in Intelligence an Existential Risk.pdf (571.42 KB)
Is Research in Intelligence an Existential Risk.pdf (571.42 KB) An Overview of Some Issues in the Theory of Deep Networks. IEEJ Transactions on Electrical and Electronic Engineering 15, 1560 - 1571 (2020).
From Marr’s Vision to the Problem of Human Intelligence. (2021). CBMM-Memo-118.pdf (362.19 KB)
CBMM-Memo-118.pdf (362.19 KB) The History of Neuroscience in Autobiography Volume 8 8, (Society for Neuroscience, 2014). Volume Introduction and Preface (232.8 KB) TomasoPoggio.pdf (1.43 MB)
Volume Introduction and Preface (232.8 KB) TomasoPoggio.pdf (1.43 MB) Compositional Sparsity of Learnable Functions. (2024). This is an update of the AMS paper (230.72 KB)
This is an update of the AMS paper (230.72 KB) Theoretical Issues in Deep Networks. (2019). CBMM Memo 100 v1 (1.71 MB) CBMM Memo 100 v3 (8/25/2019) (1.31 MB) CBMM Memo 100 v4 (11/19/2019) (1008.23 KB)
CBMM Memo 100 v1 (1.71 MB) CBMM Memo 100 v3 (8/25/2019) (1.31 MB) CBMM Memo 100 v4 (11/19/2019) (1008.23 KB) Theoretical issues in deep networks. Proceedings of the National Academy of Sciences 201907369 (2020). doi:10.1073/pnas.1907369117 PNASlast.pdf (915.3 KB)
PNASlast.pdf (915.3 KB)