Q. Liao

发表

A Surprising Linear Relationship Predicts Test Performance in Deep Networks pdf

Tomaso A. Poggio, Brando Miranda, Qianli Liao, 2018, ArXiv.

Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review

Lorenzo Rosasco, Tomaso A. Poggio, Brando Miranda, 2016, International Journal of Automation and Computing.

Theory of Deep Learning III : the non-overfitting puzzle

T. Poggio, H. Mhaskar, L. Rosasco, 2018 .

Memo No . 067 June 27 , 2017 Theory of Deep Learning III : Generalization Properties of SGD

T. Poggio, Chiyuan Zhang, A. Rakhlin, 2017 .

Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex pdf

Tomaso A. Poggio, Qianli Liao, T. Poggio, 2016, ArXiv.

Theory of Deep Learning III: explaining the non-overfitting puzzle pdf

Lorenzo Rosasco, Tomaso A. Poggio, Kenji Kawaguchi, 2017, ArXiv.

Musings on Deep Learning: Properties of SGD

Noah Golowich, Karthik Sridharan, Tomaso Poggio, 2017 .

How Important Is Weight Symmetry in Backpropagation? pdf

Joel Z. Leibo, Tomaso A. Poggio, Qianli Liao, 2015, AAAI.

Learning Functions: When Is Deep Better Than Shallow

Tomaso Poggio, Qianli Liao, Hrushikesh Mhaskar, 2016, 1603.00988.

When and Why Are Deep Networks Better Than Shallow Ones?

Tomaso A. Poggio, Qianli Liao, Hrushikesh Mhaskar, 2017, AAAI.

Biologically-plausible learning algorithms can scale to large datasets pdf

Tomaso A. Poggio, Qianli Liao, Honglin Chen, 2018, ICLR.

Exact Equivariance, Disentanglement and Invariance of Transformations

T. Poggio, Q. Liao, 2017 .

Dynamics and Neural Collapse in Deep Classifiers trained with the Square Loss

Mengjia Xu, Qianli Liao, Andrzej Banburski, 2021 .

Generalization in deep network classifiers trained with the square loss1

Tomaso Poggio, Qianli Liao, T. Poggio, 2020 .

Memo No . 90 March 3 , 2019 Theory III : Dynamics and Generalization in Deep Networks 1

T. Poggio, L. Rosasco, B. Miranda, 2019 .

3 A semi-rigorous theory of the optimization landscape of Deep Nets : Bezout theorem and Boltzman distribution

T. Poggio, B. Miranda, Q. Liao, 2019 .

Memo No . 90 April 11 , 2019 Theory III : Dynamics and Generalization in Deep Networks-a simple solution 1

T. Poggio, B. Miranda, Q. Liao, 2019 .

Memo No . 90 September 8 , 2019 Theory III : Dynamics and Generalization in Deep Networks 1

Fernanda De La Torre, T. Poggio, B. Miranda, 2019 .

No . 90 October 12 , 2019 Theory III : Dynamics and Generalization in Deep Networks 1

Fernanda De La Torre, T. Poggio, B. Miranda, 2019 .

Memo No . 90 July 18 , 2019 Theory III : Dynamics and Generalization in Deep Networks 1

T. Poggio, L. Rosasco, B. Miranda, 2019 .

Memo No . 90 August 6 , 2019 Theory III : Dynamics and Generalization in Deep Networks 1

Fernanda De La Torre, T. Poggio, B. Miranda, 2019 .

Theory IIIb: Generalization in Deep Networks

T. Poggio, X. Boix, B. Miranda, 2018, ArXiv.

Memo No . 067 December 26 , 2017 Musings on Deep Learning : Properties of SGD by

T. Poggio, Chiyuan Zhang, A. Rakhlin, 2017 .

Frequent Directions for Matrix Sketching with Provable Bounds: A Generalized Approach

Q. Liao, 2020 .

No . 066 June 23 , 2017 Theory of Deep Learning II : Landscape of the Empirical Risk in Deep Learning by

Q. Liao, 2017 .

Memo No . 072 December 27 , 2017 Theory of Deep Learning IIb : Optimization Properties of SGD by

T. Poggio, Chiyuan Zhang, A. Rakhlin, 2017 .

3 D Object-Oriented Learning : An End-to-end Transformation-Disentangled 3 D Representation by Qianli

Q. Liao, 2017 .

Deep Classiﬁers trained with the Square Loss

T. Poggio, Q. Liao, Andrzej Banburski, 2022 .

Object-Oriented Deep Learning

Tomaso Poggio, Tomaso Poggio, Qianli Liao, 2017 .

Dynamics in Deep Classifiers Trained with the Square Loss: Normalization, Low Rank, Neural Collapse, and Generalization Bounds

T. Poggio, Q. Liao, Andrzej Banburski, 2023, Research.

Towards more biologically plausible deep learning and visual processing

Qianli Liao, Q. Liao, 2017 .

The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex

Joel Z. Leibo, Tomaso A. Poggio, Qianli Liao, 2014, bioRxiv.

The invariance hypothesis implies domain-specific regions in visual cortex

Tomaso Poggio, Joel Z. Leibo, Qianli Liao, 2014 .

Theoretical Issues in Deep Networks: Approximation, Optimization and Generalization pdf

Tomaso A. Poggio, Qianli Liao, Andrzej Banburski, 2019, ArXiv.

Explicit regularization and implicit bias in deep network classifiers trained with the square loss pdf

Qianli Liao, Tomaso Poggio, T. Poggio, 2020, ArXiv.

Theoretical issues in deep networks

Qianli Liao, Andrzej Banburski, Tomaso Poggio, 2020, Proceedings of the National Academy of Sciences.

View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric Neural Tuning to Head Orientation

Joel Z. Leibo, Tomaso A. Poggio, Qianli Liao, 2016, Current Biology.

PyVar: An Extensible Framework for Variant Annotator Comparison

Qianli Liao, Julie Wertz, Thomas B Bair, 2016, bioRxiv.

Learning invariant representations and applications to face verification

Joel Z. Leibo, Tomaso A. Poggio, Qianli Liao, 2013, NIPS.

Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review

T. Poggio, H. Mhaskar, L. Rosasco, 2017, International Journal of Automation and Computing.

Theory IIIb: Generalization in Deep Networks pdf

Tomaso A. Poggio, Brando Miranda, Qianli Liao, 2018, ArXiv.

Implicit dynamic regularization in deep networks

Qianli Liao, Tomaso Poggio, T. Poggio, 2020 .

Theory III: Dynamics and Generalization in Deep Networks pdf

Lorenzo Rosasco, Tomaso A. Poggio, Brando Miranda, 2019, ArXiv.

Subtasks of Unconstrained Face Recognition

Joel Z. Leibo, Tomaso A. Poggio, Qianli Liao, 2014, 2014 International Conference on Computer Vision Theory and Applications (VISAPP).

Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines? pdf

Joel Z. Leibo, Tomaso A. Poggio, Youssef Mroueh, 2013, ArXiv.

Theory II: Landscape of the Empirical Risk in Deep Learning pdf

Tomaso A. Poggio, Qianli Liao, T. Poggio, 2017, ArXiv.

Complexity control by gradient descent in deep networks

T. Poggio, Q. Liao, Andrzej Banburski, 2020, Nature Communications.

No . 067 April 4 , 2017 Theory of Deep Learning III : Generalization Properties of SGD by

Tomaso Poggio, Noah Golowich, Karthik Sridharan, 2017 .

Unsupervised learning of clutter-resistant visual representations from natural videos pdf

Joel Z. Leibo, Tomaso A. Poggio, Qianli Liao, 2014, ArXiv.

Learning Real and Boolean Functions: When Is Deep Better Than Shallow pdf

Tomaso A. Poggio, Qianli Liao, Hrushikesh Mhaskar, 2016, ArXiv.

Generalization Puzzles in Deep Networks

Lorenzo Rosasco, Brando Miranda, Qianli Liao, 2019 .

Theoretical issues in deep networks

T. Poggio, Q. Liao, Andrzej Banburski, 2019, Proceedings of the National Academy of Sciences.

Complexity control by gradient descent in deep networks

Tomaso Poggio, Qianli Liao, Andrzej Banburski, 2020, Nature Communications.

Theory of Deep Learning IIb: Optimization Properties of SGD pdf

Tomaso A. Poggio, Noah Golowich, Brando Miranda, 2018, ArXiv.

Theory II: Landscape of the Empirical Risk in Deep Learning

T. Poggio, Q. Liao, 2017, ArXiv.

3D Object-Oriented Learning: An End-to-end Transformation-Disentangled 3D Representation

Tomaso Poggio, Qianli Liao, T. Poggio, 2017 .