Tomaso Poggio

Tomaso Poggio
Tomaso
Poggio
Director Research Module Co-Leader
Department:  BCS
Lab Affiliation(s):  CSAIL, McGovern,CiSBI

Associated Research Module: 

Associated Research Thrust: 

Tomaso A. Poggio, is the Eugene McDermott Professor at the Department of Brain and Cognitive Sciences; Director, Center for Brains, Minds and Machines; Member of the Computer Science and Artificial Intelligence Laboratory at MIT; since 2000, member of the faculty of the McGovern Institute for Brain Research. 

Born in Genoa, Italy (naturalized in 1994), he received his Doctor in Theoretical Physics from the University of Genoa in 1971 and was a Wissenschaftlicher Assistant, Max Planck Institut für Biologische Kybernetik, Tüebingen, Germany from 1972 until 1981 when he became Associate Professor at MIT. He is an honorary member of the Neuroscience Research Program, a member of the American Academy of Arts and Sciences and a Founding Fellow of AAAI. He received several awards such as the Otto-Hahn-Medaille Award  of the Max-Planck-Society, the Max Planck Research Award (with M. Fahle), from the Alexander von Humboldt Foundation, the MIT 50K Entrepreneurship Competition Award, the Laurea Honoris Causa from the University of Pavia in 2000 (Volta Bicentennial), the 2003 Gabor Award, the 2009 Okawa prize, the American Association for the Advancement of Science (AAAS) Fellowship (2009) and the Swartz Prize for Theoretical and Computational Neuroscience in 2014. He is one of the most cited computational neuroscientists (with a h-index greater than 100 – based on GoogleScholar). A former Corporate Fellow of Thinking Machines Corporation and a former director of PHZ Capital Partners, Inc., is a director of Mobileye and was involved in starting, or investing in, several other high tech companies including Arris Pharmaceutical, nFX, Imagen, Digital Persona and Deep Mind. Among his PhD students and post-docs are some of the today’s leaders in the Science and in the Engineering of Intelligence,  from Christof Koch (President and Chief Scientific Officer, Allen Institute) to Amnon Shashua (CTO and founder, Mobileye) and Demis Hassabis (CEO and founder, Deep Mind).

Email:  tp@ai.mit.edu
Website: 

Current Advisees

Frederico Azevedo - Postdoctoral researcher
Andrzej Banburski - Postdoc
Xavier Boix - Postdoctoral Associate
Vanessa D'Amario - Postdoc
Maria Fernanda De La Torre - Post baccalaureate
Arturo Deza - Postdoc
Yena Han - Graduate Student
Gil Kur - Graduate Student
Qianli Liao - Graduate Student
Akshay Rangamani - Postdoc

Past Advisees

Guy Ben-Yosef - Research Scientist
Ira Ceka - Visiting Research Intern
Georgios Evangelopoulos - Research Scientist
Noah Golowich - Visiting Student
Gabe Hege - Graduate Student
Erwin Hilton - Graduate Student
Wouter Kool - Postdoctoral Fellow
Owen Lewis - Graduate Student
Boying Meng - Graduate Student
Brando Miranda - Research Assistant
Andrea Tacchetti - Graduate Student
David Walter - Graduate Student
Zihao Xu - Graduate Student
Chiyuan Zhang - Graduate Student

Projects

Biologically Plausible Implementations of i-theory for feedforward face recognition and object recognition in the ventral stream
Computational architectures mediating object recognition under occlusion
Developmental dynamics of selectivity and invariance in macaque inferotemporal cortex
Invariance and Selectivity in Representation Learning
Invariant Representation Learning for Speech Recognition
Invariant representations for action recognition in the human visual system
Learning and Reasoning in Symbolic Domains
Neural representations of space, time and motion
The computational role of eccentricity dependent resolution in the retina: consequences for hierarchical models of object recognition
Visual processing with minimal recognizable configurations

CBMM Publications

M. Vuyyuru Reddy, Banburski, A., Pant, N., and Poggio, T., “Biologically Inspired Mechanisms for Adversarial Robustness”. 2020.
A. Deza, Liao, Q., Banburski, A., and Poggio, T., “Hierarchically Local Tasks and Deep Convolutional Networks”. 2020.
A. Rangamani, Rosasco, L., and Poggio, T., “For interpolating kernel machines, the minimum norm ERM solution is the most stable”. 2020.
W. Xiao, Chen, H., Liao, Q., and Poggio, T., “Biologically-plausible learning algorithms can scale to large datasets.”, in International Conference on Learning Representations, (ICLR 2019), 2019.
A. Banburski, Liao, Q., Miranda, B., Rosasco, L., Hidary, J., and Poggio, T., “Dynamics & Generalization in Deep Networks -Minimizing the Norm”, in NAS Sackler Colloquium on Science of Deep Learning, Washington D.C., 2019.
Y. Han, Roig, G., Geiger, G., and Poggio, T., “Properties of invariant object recognition in human one-shot learning suggests a hierarchical architecture different from deep convolutional neural networks”, in Vision Science Society, Florida, USA, 2019.
A. Banburski, Liao, Q., Miranda, B., Rosasco, L., Hidary, J., and Poggio, T., “Weight and Batch Normalization implement Classical Generalization Bounds ”, in ICML, Long Beach/California, 2019.
A. Adler, Araya-Polo, M., and Poggio, T., “Deep Recurrent Architectures for Seismic Tomography”, in 81st EAGE Conference and Exhibition 2019, 2019.
T. Poggio, Banburski, A., and Liao, Q., “Theoretical Issues in Deep Networks”. 2019.
Q. Liao, Banburski, A., and Poggio, T., “Theories of Deep Learning: Approximation, Optimization and Generalization ”, TECHCON 2019. 2019.
T. Poggio, Kur, G., and Banburski, A., “Double descent in the condition number”. 2019.
L. Isik, Tacchetti, A., and Poggio, T., “A fast, invariant representation for human action in the visual system”, Journal of Neurophysiology, 2018.
T. Poggio and Liao, Q., “Theory II: Deep learning and optimization”, Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 66, no. 6, 2018.
T. Poggio and Liao, Q., “Theory I: Deep networks and the curse of dimensionality”, Bulletin of the Polish Academy of Sciences: Technical Sciences, vol. 66, no. 6, 2018.
H. Mhaskar and Poggio, T., “An analysis of training and generalization errors in shallow and deep networks”. 2018.
A. Banburski, Liao, Q., Miranda, B., Poggio, T., Rosasco, L., Hidary, J., and De La Torre, F., “Theory III: Dynamics and Generalization in Deep Networks”. 2018.
Q. Liao, Miranda, B., Hidary, J., and Poggio, T., “Classical generalization bounds are surprisingly tight for Deep Networks”. 2018.
A. Tacchetti, Isik, L., and Poggio, T., “Invariant Recognition Shapes Neural Representations of Visual Input”, Annual Review of Vision Science, vol. 4, no. 1, pp. 403 - 422, 2018.
L. Arend, Han, Y., Schrimpf, M., Bashivan, P., Kar, K., Poggio, T., DiCarlo, J. J., and Boix, X., “Single units in a deep neural network functionally correspond with neurons in the brain: preliminary results”. 2018.
W. Xiao, Chen, H., Liao, Q., and Poggio, T., “Biologically-plausible learning algorithms can scale to large datasets”. 2018.
K. M. Villalobos, Dozier, J., Stih, V., Francl, A., Azevedo, F., Poggio, T., Sasaki, T., and Boix, X., “Can Deep Neural Networks Do Image Segmentation by Understanding Insideness?”. 2018.
Y. Han, Roig, G., Geiger, G., and Poggio, T., “Is the Human Visual System Invariant to Translation and Scale?”, in AAAI Spring Symposium Series, Science of Intelligence, 2017.
J. Mutch, Anselmi, F., Tacchetti, A., Rosasco, L., Leibo, J. Z., and Poggio, T., “Invariant Recognition Predicts Tuning of Neurons in Sensory Cortex”, in Computational and Cognitive Neuroscience of Vision, Springer, 2017, pp. 85-104.
A. Tacchetti, Isik, L., and Poggio, T., “Invariant recognition drives neural representations of action sequences”, PLoS Comp. Bio, 2017.
G. Roig, Chen, F., Boix, X., and Poggio, T., “Eccentricity Dependent Deep Neural Networks for Modeling Human Vision”, Vision Sciences Society. 2017.
H. Mhaskar, Liao, Q., and Poggio, T., “When and Why Are Deep Networks Better Than Shallow Ones?”, AAAI-17: Thirty-First AAAI Conference on Artificial Intelligence. 2017.
Y. Han, Roig, G., Geiger, G., and Poggio, T., “On the Human Visual System Invariance to Translation and Scale”, Vision Sciences Society. 2017.
A. Tacchetti, Voinea, S., Evangelopoulos, G., and Poggio, T., “Representation Learning from Orbit Sets for One-shot Classification”, in AAAI Spring Symposium Series, Science of Intelligence, AAAI, 2017.
F. Chen, Roig, G., Isik, L., Boix, X., and Poggio, T., “Eccentricity Dependent Deep Neural Networks: Modeling Invariance in Human Vision”, in AAAI Spring Symposium Series, Science of Intelligence, 2017.
J. Z. Leibo, Liao, Q., Anselmi, F., Freiwald, W. A., and Poggio, T., “View-Tolerant Face Recognition and Hebbian Learning Imply Mirror-Symmetric Neural Tuning to Head Orientation”, Current Biology, vol. 27, pp. 1-6, 2017.
V. Chandrasekhar, Lin, J., Liao, Q., Morère, O., Veillard, A., Duan, L., and Poggio, T., “Compression of Deep Neural Networks for Image Instance Retrieval”, 2017.
T. Poggio and Liao, Q., “Theory II: Landscape of the Empirical Risk in Deep Learning”. 2017.
T. Poggio, Mhaskar, H., Rosasco, L., Miranda, B., and Liao, Q., “Why and when can deep-but not shallow-networks avoid the curse of dimensionality: A review”, International Journal of Automation and Computing, pp. 1-17, 2017.
C. Zhang, Liao, Q., Rakhlin, A., Sridharan, K., Miranda, B., Golowich, N., and Poggio, T., “Musings on Deep Learning: Properties of SGD”. 2017.
F. Anselmi, Evangelopoulos, G., Rosasco, L., and Poggio, T., “Symmetry Regularization”. 2017.
A. Volokitin, Roig, G., and Poggio, T., “Do Deep Neural Networks Suffer from Crowding?”. 2017.
G. Manek, Lin, J., Chandrasekhar, V., Duan, L., Giduthuri, S., Li, X., and Poggio, T., “Pruning Convolutional Neural Networks for Image Instance Retrieval”, 2017.
Q. Liao and Poggio, T., “Object-Oriented Deep Learning”. 2017.
A. Tacchetti, Isik, L., and Poggio, T., “Invariant action recognition dataset”. 2017.
T. Liang, Poggio, T., Rakhlin, A., and Stokes, J., “Fisher-Rao Metric, Geometry, and Complexity of Neural Networks”, 2017.
L. Isik, Tacchetti, A., and Poggio, T., “A fast, invariant representation for human action in the visual system.”, J Neurophysiol, p. jn.00642.2017, 2017.
A. Tacchetti, Isik, L., and Poggio, T., “Invariant recognition drives neural representations of action sequences”, PLOS Computational Biology, vol. 13, no. 12, p. e1005859, 2017.
T. Poggio, Kawaguchi, K., Liao, Q., Miranda, B., Rosasco, L., Boix, X., Hidary, J., and Mhaskar, H., “Theory of Deep Learning III: explaining the non-overfitting puzzle”. 2017.
C. Zhang, Liao, Q., Rakhlin, A., Miranda, B., Golowich, N., and Poggio, T., “Theory of Deep Learning IIb: Optimization Properties of SGD”. 2017.
O. Lewis and Poggio, T., “Object and Scene Perception”, in From Neuron to Cognition via Computational Neuroscience, Cambridge, MA, USA: The MIT Press, 2016.
M. Nickel, Rosasco, L., and Poggio, T., “Holographic Embeddings of Knowledge Graphs”, in Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, Arizona, USA, 2016.
F. Bach and Poggio, T., “Introduction Special issue: Deep learning”, Information and Inference, vol. 5, pp. 103-104, 2016.
H. Mhaskar, Liao, Q., and Poggio, T., “Learning Functions: When Is Deep Better Than Shallow”. 2016.
Q. Liao, Leibo, J. Z., and Poggio, T., “How Important Is Weight Symmetry in Backpropagation?”, in Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, AZ., 2016.
A. Tacchetti, Isik, L., and Poggio, T., “Spatio-temporal convolutional networks explain neural representations of human actions”, 2016.
H. N. Mhaskar and Poggio, T., “Deep vs. shallow networks: An approximation theory perspective”, Analysis and Applications, vol. 14, no. 06, pp. 829 - 848, 2016.
Y. Luo, Boix, X., Roig, G., Poggio, T., and Zhao, Q., “Foveation-based Mechanisms Alleviate Adversarial Examples”. 2016.
L. Isik, Tacchetti, A., and Poggio, T., “Fast, invariant representation for human action in the visual system”. 2016.
O. Morère, Veillard, A., Lin, J., Petta, J., Chandrasekhar, V., and Poggio, T., “Group Invariant Deep Representations for Image Instance Retrieval”. 2016.
O. Morère, Veillard, A., Chandrasekhar, V., and Poggio, T., “Nested Invariance Pooling and RBM Hashing for Image Instance Retrieval”, arXiv.org, 2016.
T. Poggio and Meyers, E., “Turing++ Questions: A Test for the Science of (Human) Intelligence.”, AI Magazine, vol. 37 , no. 1, pp. 73-77, 2016.
C. Tan and Poggio, T., “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 , vol. 1(3): e0150980, 2016.
Q. Liao and Poggio, T., “Bridging the Gaps Between Residual Learning, Recurrent Neural Networks and Visual Cortex”. 2016.
T. Poggio, “Deep Learning: mathematics and neuroscience”. 2016.
F. Anselmi, Rosasco, L., and Poggio, T., “On invariance and selectivity in representation learning”, Information and Inference: A Journal of the IMA, p. iaw009, 2016.
J. Z. Leibo, Liao, Q., Freiwald, W. A., Anselmi, F., and Poggio, T., “View-tolerant face recognition and Hebbian learning imply mirror-symmetric neural tuning to head orientation”. 2016.
H. Mhaskar and Poggio, T., “Deep vs. shallow networks : An approximation theory perspective”. 2016.
T. Poggio and Anselmi, F., Visual Cortex and Deep Networks: Learning Invariant Representations. Cambridge, MA, USA: The MIT Press, 2016, p. 136.
Q. Liao, Kawaguchi, K., and Poggio, T., “Streaming Normalization: Towards Simpler and More Biologically-plausible Normalizations for Online and Recurrent Learning”. 2016.
T. Poggio, Mhaskar, H., Rosasco, L., Miranda, B., and Liao, Q., “Theory I: Why and When Can Deep Networks Avoid the Curse of Dimensionality?”. 2016.
T. Poggio, “Deep Leaning: Mathematics and Neuroscience”, A Sponsored Supplement to Science, vol. Brain-Inspired intelligent robotics: The intersection of robotics and neuroscience, pp. 9-12, 2016.
Q. Liao, Leibo, J. Z., and Poggio, T., “How Important Is Weight Symmetry in Backpropagation?”, in Thirtieth AAAI Conference on Artificial Intelligence (AAAI-16), Phoenix, AZ., 2016.
T. Poggio, Rosasco, L., Shashua, A., Cohen, N., and Anselmi, F., “Notes on Hierarchical Splines, DCLNs and i-theory”. 2015.
L. Isik, Tacchetti, A., and Poggio, T., “Invariant representations for action recognition in the visual system”, Computational and Systems Neuroscience. 2015.
C. Frogner, Zhang, C., Mobahi, H., Araya-Polo, M., and Poggio, T., “Learning with a Wasserstein Loss”, in Advances in Neural Information Processing Systems (NIPS 2015) 28, 2015.
A. Tacchetti, Isik, L., and Poggio, T., “Invariant representations for action recognition in the visual system.”, Vision Sciences Society, vol. 15, no. 12. Journal of vision, 2015.
Y. Mroueh, Voinea, S., and Poggio, T., “Learning with Group Invariant Features: A Kernel Perspective”, in NIPS 2015, 2015.
F. Anselmi, Rosasco, L., and Poggio, T., “On Invariance and Selectivity in Representation Learning”. 2015.
F. Anselmi, Rosasco, L., Tan, C., and Poggio, T., “Deep Convolutional Networks are Hierarchical Kernel Machines”. 2015.
T. Poggio, “What if..”. 2015.
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised learning of invariant representations”, Theoretical Computer Science, 2015.
J. Z. Leibo, Liao, Q., Anselmi, F., and Poggio, T., “The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex”. 2015.
C. Koch and Poggio, T., “A Science of Intelligence ”. 2015.
C. Zhang, Voinea, S., Evangelopoulos, G., Rosasco, L., and Poggio, T., “Discriminative Template Learning in Group-Convolutional Networks for Invariant Speech Representations”, in INTERSPEECH-2015, Dresden, Germany, 2015.
J. Z. Leibo, Liao, Q., Anselmi, F., and Poggio, T., “The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex”, PLOS Computational Biology, vol. 11, no. 10, p. e1004390, 2015.
M. Nickel, Rosasco, L., and Poggio, T., “Holographic Embeddings of Knowledge Graphs”. 2015.
Q. Liao, Leibo, J. Z., and Poggio, T., “How Important is Weight Symmetry in Backpropagation?”. 2015.
T. Poggio, Anselmi, F., and Rosasco, L., “I-theory on depth vs width: hierarchical function composition”. 2015.
C. Zhang, Voinea, S., Evangelopoulos, G., Rosasco, L., and Poggio, T., “Phone Classification by a Hierarchy of Invariant Representation Layers”, in INTERSPEECH 2014 - 15th Annual Conf. of the International Speech Communication Association, Singapore, 2014.
S. Voinea, Zhang, C., Evangelopoulos, G., Rosasco, L., and Poggio, T., “Word-level Invariant Representations From Acoustic Waveforms”, in INTERSPEECH 2014 - 15th Annual Conf. of the International Speech Communication Association, Singapore, 2014.
L. Isik, Meyers, E., Leibo, J. Z., and Poggio, T., “The dynamics of invariant object recognition in the human visual system.”. 2014.
J. Z. Leibo, Liao, Q., and Poggio, T., “Subtasks of unconstrained face recognition”. 2014.
J. Z. Leibo, Liao, Q., and Poggio, T., “Subtasks of Unconstrained Face Recognition”. 9th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications. (VISAPP)., Lisbon, Portugal, 2014.
L. Isik, Meyers, E., Leibo, J. Z., and Poggio, T., “The dynamics of invariant object recognition in the human visual system.”, J Neurophysiol, vol. 111, no. 1, pp. 91-102, 2014.
Q. Liao, Leibo, J. Z., and Poggio, T., “Learning invariant representations and applications to face verification”, in NIPS 2013, Lake Tahoe, Nevada, 2014.
Q. Liao, Leibo, J. Z., Mroueh, Y., and Poggio, T., “Can a biologically-plausible hierarchy effectively replace face detection, alignment, and recognition pipelines?”. 2014.
C. Zhang, Evangelopoulos, G., Voinea, S., Rosasco, L., and Poggio, T., “A Deep Representation for Invariance And Music Classification”. 2014.
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning?”. 2014.
J. Z. Leibo, Liao, Q., Anselmi, F., and Poggio, T., “The Invariance Hypothesis Implies Domain-Specific Regions in Visual Cortex”. 2014.
C. Zhang, Evangelopoulos, G., Voinea, S., Rosasco, L., and Poggio, T., “A Deep Representation for Invariance and Music Classification”, in ICASSP 2014 - 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, Florence, Italy, 2014.
G. Evangelopoulos, Voinea, S., Zhang, C., Rosasco, L., and Poggio, T., “Learning An Invariant Speech Representation”. 2014.
C. Tan and Poggio, T., “Neural tuning size is a key factor underlying holistic face processing.”. 2014.
T. Poggio, Mutch, J., and Isik, L., “Computational role of eccentricity dependent cortical magnification.”. 2014.
Q. Liao, Leibo, J. Z., and Poggio, T., “Unsupervised learning of clutter-resistant visual representations from natural videos.”. 2014.
S. Voinea, Zhang, C., Evangelopoulos, G., Rosasco, L., and Poggio, T., “Speech Representations based on a Theory for Learning Invariances”. SANE 2014 - Speech and Audio in the Northeast, 2014.
F. Anselmi and Poggio, T., “Representation Learning in Sensory Cortex: a theory.”. 2014.
T. Poggio, “Is Research in Intelligence an Existential Risk?”. 2014.
S. Villa, Rosasco, L., Poggio, T., Schölkopf, B., Luo, Z., and Vovk, V., “On Learnability, Complexity and Stability”, in Empirical Inference, Berlin, Heidelberg: Springer Berlin Heidelberg, 2013, pp. 59 - 69.
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised Learning of Invariant Representations in Hierarchical Architectures.”. 2013.
E. Lattman, Poggio, T., and Westervelt, R., “NSF Science and Technology Centers – The Class of 2013”. North America Gender Summit, Washington, D.C., 2013.
E. Garrote, Jhuang, H., Huehne, H., Poggio, T., and Serre, T., “A Large Video Database for Human Motion Recognition”. 2011.
E. Garrote, Jhuang, H., Khilnani, V., Poggio, T., Serre, T., and Yu, X., “System for Mouse Behavior Recognition”. 2010.
J. Mutch, Knoblich, U., and Poggio, T., “CNS (“Cortical Network Simulator”): a GPU-based framework for simulating cortically-organized networks”. 2010.