| Why and when can deep-but not shallow-networks avoid the curse of dimensionality: a review T Poggio, H Mhaskar, L Rosasco, B Miranda, Q Liao International Journal of Automation and Computing 14 (5), 503-519, 2017 | 156 | 2017 |
| Theory of Deep Learning III: explaining the non-overfitting puzzle T Poggio, K Kawaguchi, Q Liao, B Miranda, L Rosasco, X Boix, J Hidary, ... arXiv preprint arXiv:1801.00173, 2017 | 36 | 2017 |
| High-performance and scalable on-chip digital Fourier transform spectroscopy DM Kita, B Miranda, D Favela, D Bono, J Michon, H Lin, T Gu, J Hu Nature communications 9 (1), 4405, 2018 | 33 | 2018 |
| Theory of deep learning iii: Generalization properties of sgd C Zhang, Q Liao, A Rakhlin, K Sridharan, B Miranda, N Golowich, ... arXiv preprint arXiv:1801.00173, 2017 | 31* | 2017 |
| Theory of deep learning IIb: Optimization properties of SGD C Zhang, Q Liao, A Rakhlin, B Miranda, N Golowich, T Poggio arXiv preprint arXiv:1801.02254, 2018 | 22 | 2018 |
| A surprising linear relationship predicts test performance in deep networks Q Liao, B Miranda, A Banburski, J Hidary, T Poggio arXiv preprint arXiv:1807.09659, 2018 | 15 | 2018 |
| Theory IIIb: Generalization in deep networks T Poggio, Q Liao, B Miranda, A Banburski, X Boix, J Hidary arXiv preprint arXiv:1806.11379, 2018 | 13 | 2018 |
| Theory of deep learning iii: the non-overfitting puzzle T Poggio, K Kawaguchi, Q Liao, B Miranda, L Rosasco, X Boix, J Hidary, ... Technical report, Technical report, CBMM memo 073, 2018 | 13 | 2018 |
| On the use of Singular Spectrum Analysis AM Tomé, D Malafaia, AR Teixeira, EW Lang arXiv preprint arXiv:1807.10679, 2018 | 6 | 2018 |
| Theory I: Why and when can deep-but not shallow-networks avoid the curse of dimensionality T Poggio, H Mhaskar, L Rosasco, B Miranda, Q Liao tech. rep., CBMM Memo, 0 | 6 | |
| High-resolution on-chip digital Fourier transform spectroscopy DM Kita, B Miranda, D Favela, D Bono, J Michon, H Lin, T Gu, J Hu CLEO: Science and Innovations, SF1A. 1, 2018 | 4 | 2018 |
| Theory III: Dynamics and Generalization in Deep Networks A Banburski, Q Liao, B Miranda, L Rosasco, B Liang, J Hidary, T Poggio arXiv preprint arXiv:1903.04991, 2019 | 2 | 2019 |
| Classical generalization bounds are surprisingly tight for Deep Networks Q Liao, B Miranda, J Hidary, T Poggio Center for Brains, Minds and Machines (CBMM), 2018 | 2 | 2018 |
| Why and when can deep–but not shallow–networks avoid the curse of dimensionality T Poggio, H Mhaskar, L Rosasco, B Miranda, Q Liao Center for Brains, Minds and Machines (CBMM) Memo No. 58, arXiv preprint …, 2016 | 2 | 2016 |
| Theory i: Why and when can deep networks avoid the curse of dimensionality? T Poggio, H Mhaskar, L Rosasco, B Miranda, Q Liao Center for Brains, Minds and Machines (CBMM), arXiv, 2016 | 1 | 2016 |
| Chip-scale Digital Fourier Transform Spectroscopy DM Kita, B Miranda, D Favela, D Bono, J Michon, H Lin, T Gu, J Hu Applied Industrial Optics: Spectroscopy, Imaging and Metrology, W3A. 1, 2019 | | 2019 |
| Chip-scale high-performance digital Fourier Transform (dFT) spectrometers DM Kita, B Miranda, C Ríos, D Favela, D Bono, J Michon, H Lin, T Gu, ... Next-Generation Spectroscopic Technologies XII 10983, 1098306, 2019 | | 2019 |
| Training hierarchical networks for function approximation B Miranda Massachusetts Institute of Technology, 2016 | | 2016 |
| Dark Cloud: A Secure File System B Miranda, M Polanco, P Cattori | | 2013 |
| Theory III: Dynamics and Generalization in Deep Networks1 T Poggio, Q Liao, B Miranda, S Rakhlin, A Banburski, L Rosasco, ... | | |
TOMASO POGGIOMcDermott Professor in Brain Sciences, MITVerified email at ai.mit.edu
