Publication
Evolving Images for Visual Neurons Using a Deep Generative Network Reveals Coding Principles and Neuronal Preferences. Cell 177, 1009 (2019).
Author's last draft (20.26 MB)
Cervelli menti algoritmi. 272 (Sperling & Kupfer, 2023). at <https://www.sperling.it/libri/cervelli-menti-algoritmi-marco-magrini>
From Associative Memories to Powerful Machines. (2021).
v1.0 (1.01 MB)
v1.3Section added August 6 on self attention (3.9 MB)
Is Research in Intelligence an Existential Risk?. (2014).
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).
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review. International Journal of Automation and Computing 1-17 (2017). doi:10.1007/s11633-017-1054-2
art%3A10.1007%2Fs11633-017-1054-2.pdf (1.68 MB)
Theory of Deep Learning III: explaining the non-overfitting puzzle. (2017).
CBMM-Memo-073.pdf (2.65 MB)
CBMM Memo 073 v2 (revised 1/15/2018) (2.81 MB)
CBMM Memo 073 v3 (revised 1/30/2018) (2.72 MB)
CBMM Memo 073 v4 (revised 12/30/2018) (575.72 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)
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)
Theoretical issues in deep networks. Proceedings of the National Academy of Sciences 201907369 (2020). doi:10.1073/pnas.1907369117
PNASlast.pdf (915.3 KB)
Turing++ Questions: A Test for the Science of (Human) Intelligence. AI Magazine 37 , 73-77 (2016).
Turing_Plus_Questions.pdf (424.91 KB)
A Perspective: Sparse Compositionality and Efficiently Computable Intelligence. (2026).
Perspective_SPCOMP-9.pdf (170.23 KB)
Theory I: Why and When Can Deep Networks Avoid the Curse of Dimensionality?. (2016).
CBMM-Memo-058v1.pdf (2.42 MB)
CBMM-Memo-058v5.pdf (2.45 MB)
CBMM-Memo-058-v6.pdf (2.74 MB)
Proposition 4 has been deleted (2.75 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)
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)
Explicit regularization and implicit bias in deep network classifiers trained with the square loss. arXiv (2020). at <https://arxiv.org/abs/2101.00072>
What if.. (2015).
What if.pdf (2.09 MB)
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)
From Marr’s Vision to the Problem of Human Intelligence. (2021).
CBMM-Memo-118.pdf (362.19 KB)
I-theory on depth vs width: hierarchical function composition. (2015).
cbmm_memo_041.pdf (1.18 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)
]