Publications – Poggio Lab

Please see this link for recent publications by the Poggio lab and CBMM: https://cbmm.mit.edu/publications

Old CBCL Publications

Year of Publication:
2018

Adler, Amir

Eve Zisselman, Amir Adler, Michael Elad, “Compressed Learning for Image Classification: A Deep Neural Network Approach”, Handbook of Numerical Analysis, Elsevier, Volume 19, 2018, Pages 3-17.

2018
Year of Publication:
2017
Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review

International Journal of Automation and Computing

2017
Year of Publication:
2017
Eccentricity Dependent Deep Neural Networks for Modeling Human Vision

Vision Sciences Society

2017
Year of Publication:
2017
On the Human Visual System Invariance to Translation and Scale

Vision Sciences Society

2017
Year of Publication:
2017
Is the Human Visual System Invariant to Translation and Scale?

AAAI Spring Symposium Series, Science of Intelligence

2017
Year of Publication:
2017
Invariant Recognition Predicts Tuning of Neurons in Sensory Cortex

Computational and Cognitive Neuroscience of Vision

2017
Year of Publication:
2017
Eccentricity Dependent Deep Neural Networks: Modeling Invariance in Human Vision

AAAI Spring Symposium Series, Science of Intelligence

2017
Year of Publication:
2017
View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation

Current Biology

27
,

2017
Year of Publication:
2016
- H. Mhaskar
- Poggio, T.
Deep vs. shallow networks : An approximation theory perspective

2016

CBMM Memo No.
54
Year of Publication:
2016
Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning

2016

CBMM Memo No.
57
Year of Publication:
2016
- Q. Liao
- Poggio, T.
Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex

2016

CBMM Memo No.
47
Year of Publication:
2016
Learning Functions: When Is Deep Better Than Shallow”

2016

CBMM Memo No.
45
Year of Publication:
2016
Foveation-based Mechanisms Alleviate Adversarial Examples

2016

CBMM Memo No.
44
Year of Publication:
2016
- T. Poggio
- Anselmi, F.
Visual Cortex and Deep Networks: Learning Invariant Representations

2016
Year of Publication:
2016

T. Poggio

Deep Learning: mathematics and neuroscience- CBMM Views & Reviews

2016
Year of Publication:
2016
- T. Poggio
- Meyers, E.M.
Turing++ Questions: A Test for the Science of (Human) Intelligence.

AI Magazine

37
,

no.
1
,

2016
Year of Publication:
2016
- T. Poggio
- Tan, C.
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
Year of Publication:
2016
- T. Poggio
- Bach, F.
Introduction Special issue: Deep learning

Information and Inference

5
,

2016
Year of Publication:
2016
Holographic Embeddings of Knowledge Graphs

Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16)

2016
Year of Publication:
2016
- T. Poggio
- Lewis, O.
Object and Scene Perception

From Neuron to Cognition via Computational Neuroscience

2016
Year of Publication:
2016

Poggio, T.

Deep Learning: Mathematics and Neuroscience

A Sponsored Supplement to Science

Brain-Inspired intelligent robotics: The intersection of robotics and neuroscience
,

2016
Year of Publication:
2016
Why and When Can Deep – but Not Shallow – Networks Avoid the Curse of Dimensionality: a Review

2016

CBMM Memo No.
58
Year of Publication:
2016
Group Invariant Deep Representations for Image Instance Retrieval

2016

CBMM Memo No.
43
Year of Publication:
2016
Fast, invariant representation for human action in the visual system

2016

CBMM Memo No.
42
Year of Publication:
2016
On invariance and selectivity in representation learning

Information and Inference: A Journal of the IMA

2016
Year of Publication:
2016
How Important Is Weight Symmetry in Backpropagation?

Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16)

2016
Year of Publication:
2015
- Koch, C.
- Poggio, T.
A Science of Intelligence

2015
Year of Publication:
2015

Poggio, T.

What If…

2015
Year of Publication:
2015
Notes on Hierarchical Splines, DCLNs and i-theory

2015

CBMM Memo No.
37
Year of Publication:
2015
“Holographic Embeddings of Knowledge Graphs”

2015

CBMM Memo No.
39
Year of Publication:
2015
Discriminative Template Learning in Group-Convolutional Networks for Invariant Speech Representations

INTERSPEECH 2015

2015
Year of Publication:
2015
I-theory on depth vs width: hierarchical function composition

2015

CBMM Memo No.
41
Year of Publication:
2015
Deep Convolutional Networks are Hierarchical Kernel Machines

2015

CBMM Memo No.
35
Year of Publication:
2015
On Invariance and Selectivity in Representation Learning

2015

CBMM Memo No.
29
Year of Publication:
2015
“A Review of Relational Machine Learning for Knowledge Graphs: From Multi-Relational Link Prediction to Automated Knowledge Graph Construction”

2015

CBMM Memo No.
28
Year of Publication:
2015
Learning with Group Invariant Features: A Kernel Perspective

NIPS 2015

2015
Year of Publication:
2015
How Important Is Weight Symmetry in Backpropagation?

2015

CBMM Memo No.
36
Year of Publication:
2015
“The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex”

PLOS Computational Biology,

11
,

2015
Year of Publication:
2014
The dynamics of invariant object recognition in the human visual system

Journal of Neurophysiology

111
,

no.
1
,

2014
Year of Publication:
2014
Learning An Invariant Speech Representation

2014

CBMM Memo No.
22
Year of Publication:
2014

Poggio, T.

Is Research in Intelligence an Existential Risk?

2014
Year of Publication:
2014
The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex

2014

CBMM Memo No.
4
Year of Publication:
2014
Word-level Invariant Representations From Acoustic Waveforms

INTERSPEECH 2014 – 15th Annual Conf. of the International Speech Communication Association

2014
Year of Publication:
2014
Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning?

Theoretical Computer Science

2014
Year of Publication:
2014
“When Computer Vision Gazes at Cognition”

2014

CBMM Memo No.
25
Year of Publication:
2014
- F. Anselmi
- Poggio, T.
Representation Learning in Sensory Cortex: a theory

2014

CBMM Memo No.
26
Year of Publication:
2014
Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?

2014

CBMM Memo No.
3
Year of Publication:
2014
Learning invariant representations and applications to face verification

NIPS 2013

2014
Year of Publication:
2014
- Anselmi, Fabio
- Poggio, Tomaso
Representation Learning in Sensory Cortex: a theory.

2014

CBMM Memo No.
26
Year of Publication:
2014
Subtasks of Unconstrained Face Recognition

9th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. (VISAPP)

2014
Year of Publication:
2014
Computational role of eccentricity dependent cortical magnification.

2014

CBMM Memo No.
17
Year of Publication:
2014
- Poggio, T.
- Tan, C.
Neural tuning size is a key factor underlying holistic face processing.

2014

CBMM Memo No.
21
Year of Publication:
2014
Speech Representations based on a Theory for Learning Invariances

SANE 2014 – Speech and Audio in the Northeast

2014
Year of Publication:
2014
Machine-learning Based Automated Fault Detection in Seismic Traces ∗

EAGE Conference and Exhibition 2014

2014
Year of Publication:
2014
A Deep Representation for Invariance And Music Classification

ICASSP 2014 – 2014 IEEE International Conference on Acoustics, Speech and Signal Processing

2014
Year of Publication:
2014
Phone Classification by a Hierarchy of Invariant Representation Layers

INTERSPEECH 2014 – 15th Annual Conf. of the International Speech Communication Association

2014
Year of Publication:
2014
Unsupervised learning of clutter-resistant visual representations from natural videos.

2014

CBMM Memo No.
23
Year of Publication:
2013
Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?

2013
Year of Publication:
2013

Meyers, E

The neural decoding toolbox

2013
Year of Publication:
2013
- Mroueh, Y
- Rosasco L.
q-ary Compressive Sensing

2013
Year of Publication:
2013
Unsupervised Learning of Invariant Representations in Hierarchical Architectures

2013
Year of Publication:
2013
Computer Science and Artificial Intelligence Laboratory Technical Report

2013
Year of Publication:
2013
- Poggio, T.
- Serre, T
Models of visual cortex

2013
Year of Publication:
2013
- Poggio, T.
- Ullman, S.
Vision: are models of object recognition catching up with the brain?

2013
Year of Publication:
2013
Does invariant recognition predict tuning of neurons in sensory cortex?

2013
Year of Publication:
2013
GURLS: a Least Squares Library for Supervised Learning

2013
Year of Publication:
2013
- Tan, C.
- Poggio, T.
Faces as a “Model Category” for Visual Object Recognition

2013
Year of Publication:
2013
On Learnability, Complexity and Stability

2013
Year of Publication:
2013
Computer Science and Artificial Intelligence Laboratory Technical Report

2013
Year of Publication:
2013
Unsupervised Learning of Invariant Representations in Hierarchical Architectures

2013
Year of Publication:
2013
Learning invariant representations and applications to face verification

2013