Publication
Export 100 results:
Filters: Author is Tomaso Poggio [Clear All Filters]
Biologically-Plausible Learning Algorithms Can Scale to Large Datasets. International Conference on Learning Representations (2019).
Deep Recurrent Architectures for Seismic Tomography. 81st EAGE Conference and Exhibition 2019 (2019).
Double descent in the condition number. (2019).
Fixing typos, clarifying error in y, best approach is crossvalidation (837.18 KB)
Fixing typos, clarifying error in y, best approach is crossvalidation (834.95 KB)
Adding bound for test error (837.4 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)



An analysis of training and generalization errors in shallow and deep networks. (2018).
CBMM-Memo-076.pdf (772.61 KB)
CBMM-Memo-076v2.pdf (2.67 MB)


Biologically-plausible learning algorithms can scale to large datasets. (2018).
CBMM-Memo-092.pdf (1.31 MB)

Classical generalization bounds are surprisingly tight for Deep Networks. (2018).
CBMM-Memo-091.pdf (1.43 MB)
CBMM-Memo-091-v2.pdf (1.88 MB)


A fast, invariant representation for human action in the visual system. Journal of Neurophysiology (2018). doi:https://doi.org/10.1152/jn.00642.2017
Invariant Recognition Shapes Neural Representations of Visual Input. Annual Review of Vision Science 4, 403 - 422 (2018).
annurev-vision-091517-034103.pdf (1.55 MB)

Single units in a deep neural network functionally correspond with neurons in the brain: preliminary results. (2018).
CBMM-Memo-093.pdf (2.99 MB)

Theory I: Deep networks and the curse of dimensionality. Bulletin of the Polish Academy of Sciences: Technical Sciences 66, (2018).
02_761-774_00966_Bpast.No_.66-6_28.12.18_K1.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)

Theory III: Dynamics and Generalization in Deep Networks. (2018).
TheoryIII_ver2 (2.67 MB)
TheoryIII_ver11 (4.17 MB)
TheoryIII_ver12 (4.74 MB)
TheoryIII_ver13 (4.75 MB)
TheoryIII_ver14 (3.89 MB)
TheoryIII_ver15 (3.9 MB)
TheoryIII_ver20 (3.91 MB)
TheoryIII_ver22 (4.97 MB)
TheoryIII_ver25 (1.19 MB)
TheoryIII_ver28 (1.17 MB)
TheoryIII_ver29 (1.17 MB)
TheoryIII_ver30 (1.17 MB)
TheoryIII_ver31 (most typos and other errors corrected in main text) (1.18 MB)
TheoryIII_ver35 (more edits; regression note in appendix) (1.56 MB)
TheoryIII_ver39 (look at footnote 5) (2.14 MB)















Compression of Deep Neural Networks for Image Instance Retrieval. (2017). at <https://arxiv.org/abs/1701.04923>
1701.04923.pdf (614.33 KB)

Do Deep Neural Networks Suffer from Crowding?. (2017).
CBMM-Memo-069.pdf (6.47 MB)

Eccentricity Dependent Deep Neural Networks for Modeling Human Vision. Vision Sciences Society (2017).
Eccentricity Dependent Deep Neural Networks: Modeling Invariance in Human Vision. AAAI Spring Symposium Series, Science of Intelligence (2017). at <https://www.aaai.org/ocs/index.php/SSS/SSS17/paper/view/15360>
paper.pdf (963.87 KB)

A fast, invariant representation for human action in the visual system. J Neurophysiol jn.00642.2017 (2017). doi:10.1152/jn.00642.2017
Author's last draft (695.63 KB)

Fisher-Rao Metric, Geometry, and Complexity of Neural Networks. arXiv.org (2017). at <https://arxiv.org/abs/1711.01530>
1711.01530.pdf (966.99 KB)

On the Human Visual System Invariance to Translation and Scale. Vision Sciences Society (2017).
Is the Human Visual System Invariant to Translation and Scale?. AAAI Spring Symposium Series, Science of Intelligence (2017).
Invariant recognition drives neural representations of action sequences. PLOS Computational Biology 13, e1005859 (2017).
journal.pcbi_.1005859.pdf (9.24 MB)

Invariant recognition drives neural representations of action sequences. PLoS Comp. Bio (2017).
Computational and Cognitive Neuroscience of Vision 85-104 (Springer, 2017).