Publication
Export 17 results:
Filters: Author is Andrzej Banburski [Clear All Filters]
Neural Collapse in Deep Homogeneous Classifiers and the role of Weight Decay. IEEE International Conference on Acoustics, Speech and Signal Processing (2022).
PCA as a defense against some adversaries. (2022). CBMM-Memo-135.pdf (2.58 MB)
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)
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)
Dreaming with ARC. Learning Meets Combinatorial Algorithms workshop at NeurIPS 2020 (2020). CBMM Memo 113.pdf (1019.64 KB)
Hierarchically Local Tasks and Deep Convolutional Networks. (2020). CBMM_Memo_109.pdf (2.12 MB)
An Overview of Some Issues in the Theory of Deep Networks. IEEJ Transactions on Electrical and Electronic Engineering 15, 1560 - 1571 (2020).
Theoretical issues in deep networks. Proceedings of the National Academy of Sciences 201907369 (2020). doi:10.1073/pnas.1907369117 PNASlast.pdf (915.3 KB)
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)
Dynamics & Generalization in Deep Networks -Minimizing the Norm. NAS Sackler Colloquium on Science of Deep Learning (2019).
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)
Theories of Deep Learning: Approximation, Optimization and Generalization . TECHCON 2019 (2019).
Theory III: Dynamics and Generalization in Deep Networks. (2018). Original, intermediate versions are available under request (2.67 MB) CBMM Memo 90 v12.pdf (4.74 MB) Theory_III_ver44.pdf Update Hessian (4.12 MB) Theory_III_ver48 (Updated discussion of convergence to max margin) (2.56 MB) fixing errors and sharpening some proofs (2.45 MB)