Tomaso Poggio

Tomaso Poggio

Auto-generated profile, based on publicly available information

Tomaso Poggio

K. Lisa Yang Integrative Computational Neuroscience Center, Yang Tan Collective, Massachusetts Institute of Technology

Research Focus & Metrics

Academic Career Length

35Years (1992-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 March 2017 in International Journal of Automation and Computing
Verified
Journal Article
Open access
PDF file
TPTomaso Poggio
Tomaso Poggio
HMHrushikesh Mhaskar
Hrushikesh Mhaskar
LRLorenzo Rosasco
Lorenzo Rosasco
BMBrando Miranda
Brando Miranda
QLQianli Liao
Qianli Liao
The paper reviews and extends an emerging body of theoretical results on deep learning including the conditions under which it can be exponentially better than shallow learning. A class of deep convolutional networks represent an important special case of these conditions, though weight sharing is not the main reason for their exponential advantage. Implications of a few key theorems are discussed, together with new results, open problems and conjectures.

1 January 2007
Verified
Conference Paper
Closed access
HJH. Jhuang
H. Jhuang
TST. Serre
T. Serre
LWL. Wolf
L. Wolf
TPT. Poggio
T. Poggio
We present a biologically-motivated system for the recognition of actions from video sequences. The approach builds on recent work on object recognition based on hierarchical feedforward architectures [25, 16, 20] and extends a neurobiological model of motion processing in the visual cortex [10]. The system consists of a hierarchy of spatio-temporal feature detectors of increasing complexity: an input sequence is first analyzed by an array of motion- direction sensitive units which, through a hierarchy of processing stages, lead to position-invariant spatio-temporal feature detectors. We experiment with different types of motion-direction sensitive units as well as different system architectures. As in [16], we find that sparse features in intermediate stages outperform dense ones and that using a simple feature selection approach leads to an efficient system that performs better with far fewer features. We test the approach on different publicly available action datasets, in all cases achieving the highest results reported to date.

13 October 2004 in Nature
Verified
Journal Article
Closed access
PDF file
TPTomaso Poggio
Tomaso Poggio
EBEmilio Bizzi
Emilio Bizzi

25 March 2004 in Nature
Verified
Journal Article
Closed access
PDF file
TPTomaso Poggio
Tomaso Poggio
RRRyan Rifkin
Ryan Rifkin
SMSayan Mukherjee
Sayan Mukherjee
PNPartha Niyogi
Partha Niyogi

9 June 2020 in Proceedings of the National Academy of Sciences
Verified
Journal Article
Closed access
PDF file
TPTomaso Poggio
Tomaso Poggio
ABAndrzej Banburski
Andrzej Banburski
QLQianli Liao
Qianli Liao
While deep learning is successful in a number of applications, it is not yet well understood theoretically. A theoretical characterization of deep learning should answer questions about their approximation power, the dynamics of optimization, and good out-of-sample performance, despite overparameterization and the absence of explicit regularization. We review our recent results toward this goal. In approximation theory both shallow and deep networks are known to approximate any continuous functions at an exponential cost. However, we proved that for certain types of compositional functions, deep networks of the convolutional type (even without weight sharing) can avoid the curse of dimensionality. In characterizing minimization of the empirical exponential loss we consider the gradient flow of the weight directions rather than the weights themselves, since the relevant function underlying classification corresponds to normalized networks. The dynamics of normalized weights turn out to be equivalent to those of the constrained problem of minimizing the loss subject to a unit norm constraint. In particular, the dynamics of typical gradient descent have the same critical points as the constrained problem. Thus there is implicit regularization in training deep networks under exponential-type loss functions during gradient flow. As a consequence, the critical points correspond to minimum norm infima of the loss. This result is especially relevant because it has been recently shown that, for overparameterized models, selection of a minimum norm solution optimizes cross-validation leave-one-out stability and thereby the expected error. Thus our results imply that gradient descent in deep networks minimize the expected error.

1 July 2006 in Advances in Computational Mathematics
Verified
Journal Article
Closed access
PDF file
SMSayan Mukherjee
Sayan Mukherjee
PNPartha Niyogi
Partha Niyogi
TPTomaso Poggio
Tomaso Poggio
RRRyan Rifkin
Ryan Rifkin