Relational inductive biases, deep learning, and graph networks PW Battaglia, JB Hamrick, V Bapst, A Sanchez-Gonzalez, V Zambaldi, ... arXiv preprint arXiv:1806.01261, 2018 | 298 | 2018 |

Visual interaction networks: Learning a physics simulator from video N Watters, D Zoran, T Weber, P Battaglia, R Pascanu, A Tacchetti Advances in neural information processing systems, 4539-4547, 2017 | 101 | 2017 |

Unsupervised learning of invariant representations in hierarchical architectures F Anselmi, JZ Leibo, L Rosasco, J Mutch, A Tacchetti, T Poggio arXiv preprint arXiv:1311.4158, 2013 | 66 | 2013 |

GURLS: A Least Squares Library for Supervised Learning A Tacchetti, P Mallapragada, M Santoro, R Rosasco Journal of Machine Learning Research 14, 3201-3205, 2013 | 53 | 2013 |

Unsupervised learning of invariant representations F Anselmi, JZ Leibo, L Rosasco, J Mutch, A Tacchetti, T Poggio Theoretical Computer Science 633, 112-121, 2016 | 47 | 2016 |

The computational magic of the ventral stream: sketch of a theory (and why some deep architectures work). T Poggio, J Mutch, J Leibo, L Rosasco, A Tacchetti | 35 | 2013 |

Unsupervised learning of invariant representations with low sample complexity: the magic of sensory cortex or a new framework for machine learning? F Anselmi, JZ Leibo, L Rosasco, J Mutch, A Tacchetti, T Poggio Center for Brains, Minds and Machines (CBMM), arXiv, 2014 | 26 | 2014 |

GURLS: a toolbox for large scale multiclass learning A Tacchetti, P Mallapragada, M Santoro, L Rosasco NIPS 2011 workshop on parallel and large-scale machine learning. http://cbcl …, 2011 | 23 | 2011 |

Magic materials: a theory of deep hierarchical architectures for learning sensory representations F Anselmi, JZ Leibo, L Rosasco, J Mutch, A Tacchetti, T Poggio CBCL paper, 2013 | 20 | 2013 |

Fast, invariant representation for human action in the visual system L Isik, A Tacchetti, T Poggio Journal of Neurophysiology 119 (2), 631-640, 2018 | 15 | 2018 |

Regularization by early stopping for online learning algorithms L Rosasco, A Tacchetti, S Villa stat 1050, 30, 2014 | 9 | 2014 |

Invariant recognition drives neural representations of action sequences A Tacchetti, L Isik, T Poggio PLoS computational biology 13 (12), e1005859, 2017 | 7 | 2017 |

Does invariant recognition predict tuning of neurons in sensory cortex? T Poggio, J Mutch, F Anselmi, A Tacchetti, L Rosasco, JZ Leibo | 7 | 2013 |

Relational forward models for multi-agent learning A Tacchetti, HF Song, PAM Mediano, V Zambaldi, NC Rabinowitz, ... arXiv preprint arXiv:1809.11044, 2018 | 6 | 2018 |

Invariant recognition predicts tuning of neurons in sensory cortex J Mutch, F Anselmi, A Tacchetti, L Rosasco, JZ Leibo, T Poggio Computational and Cognitive Neuroscience of Vision, 85-104, 2017 | 5 | 2017 |

Spatio-temporal convolutional neural networks explain human neural representations of action recognition A Tacchetti, L Isik, T Poggio arXiv preprint arXiv:1606.04698 2, 2016 | 5 | 2016 |

Magic Materials: a theory of deep hierarchical architectures for learning sensory representations CBCL paper F Anselmi, JZ Leibo, L Rosasco, J Mutch, A Tacchetti, T Poggio Massachusetts Institute of Technology, Cambridge, MA, 2013 | 5 | 2013 |

Implementation and tuning of the extended Kalman filter for a sensorless drive working with arbitrary stepper motors and cable lengths M Butcher, A Masi, M Martino, A Tacchetti 2012 XXth International Conference on Electrical Machines, 2216-2222, 2012 | 5 | 2012 |

Invariances determine the hierarchical architecture and the tuning properties of the ventral stream T Poggio, J Mutch, F Anselmi, JZ Leibo, L Rosasco, A Tacchetti Technical Report available online, MIT CBCL, 2013. Previously released as …, 2011 | 5 | 2011 |

Invariant recognition shapes neural representations of visual input A Tacchetti, L Isik, TA Poggio Annual review of vision science 4, 403-422, 2018 | 3 | 2018 |