Publications

CBMM Memos were established in 2014 as a mechanism for our center to share research results with the wider scientific community. Click here to read more about the memos and to see a full list of the memos.

Videos
Support Us

Publication

Search

Show only items where

Author

Type

Term

Year

Keyword

Found 160 results

Author Title [ Type

] Year

Filters: Author is Tomaso Poggio [Clear All Filters]

CBMM Memos

Anselmi, F. & Poggio, T. Representation Learning in Sensory Cortex: a theory. (2014).

CBMM-Memo-026_neuron_ver45.pdf (1.35 MB)

Gan, Y., Galanti, T., Poggio, T. & Malach, E. On the Power of Decision Trees in Auto-Regressive Language Modeling. (2024).

CBMM-Memo-149.pdf (2.11 MB)

Danhofer, D. A., D’Ascenzo, D., Dubach, R. & Poggio, T. Position: A Theory of Deep Learning Must Include Compositional Sparsity. (2025).

CBMM Memo 159.pdf (676.35 KB)

Poggio, T. A Perspective: Sparse Compositionality and Efficiently Computable Intelligence. (2026).

Perspective_SPCOMP-9.pdf (170.23 KB)

Gupte, A., Banburski, A. & Poggio, T. PCA as a defense against some adversaries. (2022).

CBMM-Memo-135.pdf (2.58 MB)

Liao, Q. & Poggio, T. Object-Oriented Deep Learning. (2017).

CBMM-Memo-070.pdf (963.54 KB)

Poggio, T., Rosasco, L., Shashua, A., Cohen, N. & Anselmi, F. Notes on Hierarchical Splines, DCLNs and i-theory. (2015).

CBMM Memo 037 (1.83 MB)

Galanti, T., Xu, M., Galanti, L. & Poggio, T. Norm-Based Generalization Bounds for Compositionally Sparse Neural Networks. (2023).

Norm-based bounds for convnets.pdf (1.2 MB)

Tan, C. & Poggio, T. Neural tuning size is a key factor underlying holistic face processing. (2014).

CBMM-Memo-021-1406.3793.pdf (387.79 KB)

Zhang, C. et al. Musings on Deep Learning: Properties of SGD. (2017).

CBMM Memo 067 v2 (revised 7/19/2017) (5.88 MB)

CBMM Memo 067 v3 (revised 9/15/2017) (5.89 MB)

CBMM Memo 067 v4 (revised 12/26/2017) (5.57 MB)

Dubach, R., Abdallah, M. S. & Poggio, T. Multiplicative Regularization Generalizes Better Than Additive Regularization. (2025).

CBMM Memo 158.pdf (4.8 MB)

Poggio, T. & Cooper, Y. 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)

Mhaskar, H., Liao, Q. & Poggio, T. Learning Functions: When Is Deep Better Than Shallow. (2016). at <https://arxiv.org/pdf/1603.00988v4.pdf>

Evangelopoulos, G., Voinea, S., Zhang, C., Rosasco, L. & Poggio, T. Learning An Invariant Speech Representation. (2014).

CBMM-Memo-022-1406.3884v1.pdf (1.81 MB)

Xu, M. et al. The Janus effects of SGD vs GD: high noise and low rank. (2023).

Updated with appendix showing empirically that the main results extend to deep nonlinear networks (2.95 MB)

Small updates...typos... (616.82 KB)

Poggio, T., Anselmi, F. & Rosasco, L. I-theory on depth vs width: hierarchical function composition. (2015).

cbmm_memo_041.pdf (1.18 MB)

Leibo, J. Z., Liao, Q., Anselmi, F. & Poggio, T. The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex. (2014). doi:10.1101/004473

CBMM Memo 004_new.pdf (2.25 MB)

Anselmi, F., Rosasco, L. & Poggio, T. On Invariance and Selectivity in Representation Learning. (2015).

CBMM Memo No. 029 (812.07 KB)

Poggio, T., Liao, Q. & Xu, M. Implicit dynamic regularization in deep networks. (2020).

v1.2 (2.29 MB)

v.59 Update on rank (2.43 MB)

Liao, Q., Leibo, J. Z. & Poggio, T. How Important is Weight Symmetry in Backpropagation?. (2015).

1510.05067v3.pdf (615.32 KB)

Poggio, T. 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)

Gan, Y. & Poggio, T. A Homogeneous Transformer Architecture. (2023).

CBMM Memo 143 v2 (1.1 MB)

Nickel, M., Rosasco, L. & Poggio, T. Holographic Embeddings of Knowledge Graphs. (2015).

holographic-embeddings.pdf (677.87 KB)

Deza, A., Liao, Q., Banburski, A. & Poggio, T. Hierarchically Local Tasks and Deep Convolutional Networks. (2020).

CBMM_Memo_109.pdf (2.12 MB)

Morère, O. et al. Group Invariant Deep Representations for Image Instance Retrieval. (2016).

CBMM-Memo-043.pdf (2.66 MB)

Pages