Andrea Tacchetti

Andrea Tacchetti
Andrea
Tacchetti
Graduate Student
Massachusetts Institute of Technology (MIT), Italian Institute of Technology (IIT)
Department:  EECS
Lab Affiliation(s):  Poggio Lab

Associated Research Thrust: 

I am a third year PhD student in the Electrical Engineering and Computer Science at MIT where I am part of the Computer Science and Artificial Intelligence Laboratory. I am advised by Tomaso Poggio in the Center for Brains, Minds, and Machines and I am part of the LCSL, a joint lab between MITand the Istituto Italiano di Tecnologia. I am interested in building systems that model and imitate how our visual cortex recognizes objects, actions and people in videos and static images under a wide variety of transformations. I also design algorithms that are able to learn from large amounts of labeled data.

In the Summer of 2014 I have worked as a Software Engineering and Research Intern at A9.com (Amazon, Inc) where I developed a Deep Learning system for object localization and recognition. In the Summer of 2013 I worked as a Data Scientist and Software Engineering Intern at Room 77, Inc (acquired by Google in 2014) where I designed and wrote algorithms for search results ranking and segmentation.

In the fall of 2013 I was a Teacher Assistant for Prof. A. Torralba's graduate level class Advances in Computer Vision (6.869). In the fall of 2014 I was a Teacher Assistant for Prof. L. Kaelbling's Machine Learning (6.867) graduate level class..

In 2010 I was part of the Equipment Controls and Electronic section in the Engineering Department at CERN where I developed a system to learn the minimum tracking error parameters for a complex control loop from measurements acquired on board.

I race bikes for the MIT Cycling Tream where I also serve as treasusrer. In the past I have been the organizer of the Machine Learning Tea at MIT for which I have secured fundings from Google. Together with M. Gharbi I am writing a vision based iPhone app called Splitsy.

Website: 
Advisor/s: 
Tomaso Poggio

Projects

Invariant representations for action recognition in the human visual system

CBMM Publications

L. Isik and Tacchetti, A., “MEG action recognition data”. 2018.
L. Isik, Tacchetti, A., and Poggio, T., “A fast, invariant representation for human action in the visual system”, Journal of Neurophysiology, 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.
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.
A. Tacchetti, Isik, L., and Poggio, T., “Invariant recognition drives neural representations of action sequences”, PLoS Comp. Bio, 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, Voinea, S., and Evangelopoulos, G., “Discriminate-and-Rectify Encoders: Learning from Image Transformation Sets”. 2017.
A. Tacchetti, Isik, L., and Poggio, T., “Invariant action recognition dataset”. 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.
A. Tacchetti, Isik, L., and Poggio, T., “Spatio-temporal convolutional networks explain neural representations of human actions”, 2016.
L. Isik, Tacchetti, A., and Poggio, T., “Fast, invariant representation for human action in the visual system”. 2016.
L. Isik, Tacchetti, A., and Poggio, T., “Invariant representations for action recognition in the visual system”, Computational and Systems Neuroscience. 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.
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised learning of invariant representations”, Theoretical Computer Science, 2015.
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.
F. Anselmi, Leibo, J. Z., Rosasco, L., Mutch, J., Tacchetti, A., and Poggio, T., “Unsupervised Learning of Invariant Representations in Hierarchical Architectures.”. 2013.