TP
Tomaso Poggio
cs.LGstat.MLcs.CVModels, Neurologicalcs.AIcs.NEq-bio.NCPattern Recognition, VisualVision, OcularAlgorithms
On Valency
published · living versionsW_9va24dn5·v1 · currentpublished
Preprints & journals
169 papers in the corpus · 1972–2025Learning Multi-Index Models with Hyper-Kernel Ridge Regression2510.02532v2 · Shuo Huang, Hippolyte Labarriere, Ernesto De Vito et al.2025 · 0 citationsarXiv
Unraveling Syntax: Language Modeling and the Substructure of Grammars2510.02524v3 · Laura Ying Schulz, Daniel Mitropolsky, Tomaso Poggio2025 · 0 citationsarXiv
Ubiquity of Emergent Hebbian Dynamics in Regularized Learning2505.18069v3 · David Koplow, Tomaso Poggio, Liu Ziyin2025 · 0 citationsarXiv
A universal compression theory for lottery ticket hypothesis and neural scaling laws2510.00504v2 · Hong-Yi Wang, Di Luo, Tomaso Poggio et al.2025 · 0 citationsarXiv
Does Feedback Alignment Work at Biological Timescales?2510.18808v2 · Marc Gong Bacvanski, Liu Ziyin, Tomaso Poggio2025 · 0 citationsarXiv
Training the Untrainable: Introducing Inductive Bias via Representational Alignment2410.20035v2 · Vighnesh Subramaniam, David Mayo, Colin Conwell et al.2024 · 0 citationsarXiv
On efficiently computable functions, deep networks and sparse compositionality2510.11942v1 · Tomaso Poggio2025 · 0 citationsarXiv
Topological Invariance and Breakdown in Learning2510.02670v1 · Yongyi Yang, Tomaso Poggio, Isaac Chuang et al.2025 · 0 citationsarXiv
Parameter Symmetry Potentially Unifies Deep Learning Theory2502.05300v2 · Liu Ziyin, Yizhou Xu, Tomaso Poggio et al.2025 · 0 citationsarXiv
Heterosynaptic Circuits Are Universal Gradient Machines2505.02248v1 · Liu Ziyin, Isaac Chuang, Tomaso Poggio2025 · 0 citationsarXiv
Formation of Representations in Neural Networks2410.03006v2 · Liu Ziyin, Isaac Chuang, Tomer Galanti et al.2024 · 1 citationarXiv
What if Eye...? Computationally Recreating Vision Evolution2501.15001v2 · Kushagra Tiwary, Aaron Young, Zaid Tasneem et al.2025 · 5 citationsarXiv
Self-Assembly of a Biologically Plausible Learning Circuit2412.20018v1 · Qianli Liao, Liu Ziyin, Yulu Gan et al.2024 · 0 citationsarXiv
SGD and Weight Decay Secretly Minimize the Rank of Your Neural Network2206.05794v7 · Tomer Galanti, Zachary S. Siegel, Aparna Gupte et al.2022 · 0 citationsarXiv
Iterative regularization in classification via hinge loss diagonal descent2212.12675v2 · Vassilis Apidopoulos, Tomaso Poggio, Lorenzo Rosasco et al.2022 · 1 citationarXiv
On the Power of Decision Trees in Auto-Regressive Language Modeling2409.19150v1 · Yulu Gan, Tomer Galanti, Tomaso Poggio et al.2024 · 0 citationsarXiv
How to guess a gradient2312.04709v1 · Utkarsh Singhal, Brian Cheung, Kartik Chandra et al.2023 · 0 citationsarXiv
System identification of neural systems: If we got it right, would we know?2302.06677v2 · Yena Han, Tomaso Poggio, Brian Cheung2023 · 1 citationarXiv
Dynamics in Deep Classifiers Trained with the Square Loss: Normalization, Low Rank, Neural Collapse, and Generalization Bounds.37223467 · Xu, Mengjia, Rangamani, Akshay, Liao, Qianli et al.2023 · 11 citationsResearch (Washington, D.C.). 2023;6:0024
Norm-based Generalization Bounds for Compositionally Sparse Neural Networks2301.12033v1 · Tomer Galanti, Mengjia Xu, Liane Galanti et al.2023 · 2 citationsarXiv
Neural-guided, Bidirectional Program Search for Abstraction and Reasoning2110.11536v2 · Simon Alford, Anshula Gandhi, Akshay Rangamani et al.2021 · 7 citationsarXiv
Distribution of Classification Margins: Are All Data Equal?2107.10199v1 · Andrzej Banburski, Fernanda De La Torre, Nishka Pant et al.2021 · 1 citationarXiv
Hierarchically Compositional Tasks and Deep Convolutional Networks2006.13915v3 · Arturo Deza, Qianli Liao, Andrzej Banburski et al.2020 · 4 citationsarXiv
The Effects of Image Distribution and Task on Adversarial Robustness2102.10534v1 · Owen Kunhardt, Arturo Deza, Tomaso Poggio2021 · 1 citationarXiv
Theoretical issues in deep networks.32518109 · Poggio, Tomaso, Banburski, Andrzej, Liao, Qianli2021 · 168 citationsProceedings of the National Academy of Sciences of the United States of America. 2020;117(48):30039-30045
Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex1604.03640v2 · Qianli Liao, Tomaso Poggio2016 · 185 citationsarXivon Valency
Explicit regularization and implicit bias in deep network classifiers trained with the square loss2101.00072v1 · Tomaso Poggio, Qianli Liao2020 · 7 citationsarXiv
CUDA-Optimized real-time rendering of a Foveated Visual System2012.08655v1 · Elian Malkin, Arturo Deza, Tomaso Poggio2020 · 3 citationsarXiv
For interpolating kernel machines, minimizing the norm of the ERM solution minimizes stability2006.15522v2 · Akshay Rangamani, Lorenzo Rosasco, Tomaso Poggio2020 · 4 citationsarXiv
Fisher-Rao Metric, Geometry, and Complexity of Neural Networks1711.01530v2 · Tengyuan Liang, Tomaso Poggio, Alexander Rakhlin et al.2017 · 121 citationsThe 22nd International Conference on Artificial Intelligence and Statistics 89 (2019) 888-896
Biologically Inspired Mechanisms for Adversarial Robustness2006.16427v1 · Manish V. Reddy, Andrzej Banburski, Nishka Pant et al.2020 · 23 citationsarXiv
Scale and translation-invariance for novel objects in human vision.31996698 · Han, Yena, Roig, Gemma, Geiger, Gad et al.2020 · 47 citationsScientific reports. 2020;10(1):1411
Double descent in the condition number1912.06190v3 · Tomaso Poggio, Gil Kur, Andrzej Banburski2019 · 13 citationsarXiv
Complexity control by gradient descent in deep networks.32094327 · Poggio, Tomaso, Liao, Qianli, Banburski, Andrzej2020 · 35 citationsNature communications. 2020;11(1):1027
Theory III: Dynamics and Generalization in Deep Networks1903.04991v5 · Andrzej Banburski, Qianli Liao, Brando Miranda et al.2019 · 5 citationsarXiv
An analysis of training and generalization errors in shallow and deep networks.31574413 · Mhaskar, H N, Poggio, T2020 · 19 citationsNeural networks : the official journal of the International Neural Network Society. 2020;121:229-241
Function approximation by deep networks1905.12882v2 · H. N. Mhaskar, T. Poggio2019 · 21 citationsarXiv
A Sparse Representation for Function Approximation.9698352 · Poggio, Girosi2019 · 84 citationsNeural computation. 1998;10(6):1445-54
An analysis of training and generalization errors in shallow and deep networks1802.06266v4 · Hrushikesh Mhaskar, Tomaso Poggio2018 · 19 citationsarXiv
Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization1908.09375v1 · Tomaso Poggio, Andrzej Banburski, Qianli Liao2019 · 19 citationsarXiv
Deep Recurrent Architectures for Seismic Tomography1908.07824v1 · Amir Adler, Mauricio Araya-Polo, Tomaso Poggio2019 · 30 citationsarXiv
Invariant Recognition Shapes Neural Representations of Visual Input.30052494 · Tacchetti, Andrea, Isik, Leyla, Poggio, Tomaso A2019 · 46 citationsAnnual review of vision science. 2018;4:403-422
A fast, invariant representation for human action in the visual system.29118198 · Isik, Leyla, Tacchetti, Andrea, Poggio, Tomaso2019 · 45 citationsJournal of neurophysiology. 2018;119(2):631-640
Biologically-plausible learning algorithms can scale to large datasets1811.03567v3 · Will Xiao, Honglin Chen, Qianli Liao et al.2018 · 47 citationsarXiv
A Surprising Linear Relationship Predicts Test Performance in Deep Networks1807.09659v1 · Qianli Liao, Brando Miranda, Andrzej Banburski et al.2018 · 21 citationsarXiv
View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric Neural Tuning to Head Orientation.27916522 · Leibo, Joel Z, Liao, Qianli, Anselmi, Fabio et al.2018 · 57 citationsCurrent biology : CB. 2017;27(1):62-67
Theory IIIb: Generalization in Deep Networks1806.11379v1 · Tomaso Poggio, Qianli Liao, Brando Miranda et al.2018 · 14 citationsarXiv
Approximate inference with Wasserstein gradient flows1806.04542v1 · Charlie Frogner, Tomaso Poggio2018 · 17 citationsarXiv
Invariant recognition drives neural representations of action sequences1606.04698v3 · Andrea Tacchetti, Leyla Isik, Tomaso Poggio2016 · 17 citationsarXiv
Theory of Deep Learning III: explaining the non-overfitting puzzle1801.00173v2 · Tomaso Poggio, Kenji Kawaguchi, Qianli Liao et al.2017 · 48 citationsarXiv
Career total: 729 works. 169 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.