Publication
Export 147 results:
Filters: Author is Tomaso A. Poggio [Clear All Filters]
Theory II: Landscape of the Empirical Risk in Deep Learning. (2017).
CBMM Memo 066_1703.09833v2.pdf (5.56 MB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Theory of Deep Learning IIb: Optimization Properties of SGD. (2017).
CBMM-Memo-072.pdf (3.66 MB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
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)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric Neural Tuning to Head Orientation. Current Biology 27, 1-6 (2017).
When and Why Are Deep Networks Better Than Shallow Ones?. AAAI-17: Thirty-First AAAI Conference on Artificial Intelligence (2017).
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)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex. (2016).
CBMM Memo No. 047 (1.29 MB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Deep Leaning: Mathematics and Neuroscience. A Sponsored Supplement to Science Brain-Inspired intelligent robotics: The intersection of robotics and neuroscience, 9-12 (2016).
Deep Learning: mathematics and neuroscience. (2016).
Deep Learning- mathematics and neuroscience.pdf (1.25 MB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Deep vs. shallow networks: An approximation theory perspective. Analysis and Applications 14, 829 - 848 (2016).
Deep vs. shallow networks : An approximation theory perspective. (2016).
Original submission, visit the link above for the updated version (960.27 KB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Fast, invariant representation for human action in the visual system. (2016). at <http://arxiv.org/abs/1601.01358>
CBMM Memo 042 (3.03 MB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Foveation-based Mechanisms Alleviate Adversarial Examples. (2016).
cbmm_memo_044.pdf (11.48 MB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Group Invariant Deep Representations for Image Instance Retrieval. (2016).
CBMM-Memo-043.pdf (2.66 MB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Holographic Embeddings of Knowledge Graphs. Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) (2016).
1510.04935v2.pdf (360.65 KB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
How Important Is Weight Symmetry in Backpropagation?. Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) (Association for the Advancement of Artificial Intelligence, 2016).
liao-leibo-poggio.pdf (191.91 KB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
How Important Is Weight Symmetry in Backpropagation?. Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16) (2016). at <https://cbmm.mit.edu/sites/default/files/publications/liao-leibo-poggio.pdf>
On invariance and selectivity in representation learning. Information and Inference: A Journal of the IMA iaw009 (2016). doi:10.1093/imaiai/iaw009
imaiai.iaw009.full_.pdf (267.87 KB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Learning Functions: When Is Deep Better Than Shallow. (2016). at <https://arxiv.org/pdf/1603.00988v4.pdf>
Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval. arXiv.org (2016). at <https://arxiv.org/abs/1603.04595>
1603.04595.pdf (2.9 MB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
Neural Tuning Size in a Model of Primate Visual Processing Accounts for Three Key Markers of Holistic Face Processing. Public Library of Science | PLoS ONE 1(3): e0150980, (2016).
journal.pone_.0150980.PDF (384.15 KB)
![application/pdf PDF icon](/modules/file/icons/application-pdf.png)
From Neuron to Cognition via Computational Neuroscience (The MIT Press, 2016). at <https://mitpress.mit.edu/neuron-cognition>