| 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 | 672 | 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 | 234 | 2018 |
| Are emergent abilities of large language models a mirage? R Schaeffer, B Miranda, S Koyejo Advances in Neural Information Processing Systems 36, 2024 | 155 | 2024 |
| 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 | 126 | 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 | 116* | 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 | 35 | 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 | 31 | 2018 |
| Theory of deep learning iii: the non-overfitting puzzle T Poggio, K Kawaguchi, Q Liao, B Miranda, L Rosasco, X Boix, J Hidary, ... CBMM Memo 73, 1-38, 2018 | 25 | 2018 |
| Theory III: Dynamics and generalization in deep networks A Banburski, Q Liao, B Miranda, L Rosasco, F De La Torre, J Hidary, ... arXiv preprint arXiv:1903.04991, 2019 | 14 | 2019 |
| Theory of deep learning III: Dynamics and generalization in deep networks A Banburski, Q Liao, B Miranda, T Poggio, L Rosasco, B Liang, J Hidary Center for Brains, Minds and Machines [CBMM], Cambridge, MA, https://arxiv …, 2019 | 14 | 2019 |
| Theory I: Why and when can deepbut 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], Cambridge, MA, 2016 | 14 | 2016 |
| Beyond scale: the diversity coefficient as a data quality metric demonstrates llms are pre-trained on formally diverse data A Lee, B Miranda, S Koyejo arXiv preprint arXiv:2306.13840, 2023 | 12 | 2023 |
| Digital Fourier transform spectroscopy: a high-performance, scalable technology for on-chip spectrum analysis DM Kita, B Miranda, D Favela, D Bono, J Michon, H Lin, T Gu, J Hu arXiv preprint arXiv:1802.05270, 2018 | 9 | 2018 |
| High-resolution on-chip digital Fourier transform spectroscopy DM Kita, B Mirandat, D Favelai, D Bono, J Michon, H Lin, T Gu, J Hu 2018 Conference on Lasers and Electro-Optics (CLEO), 1-2, 2018 | 5 | 2018 |
| Sketching: a Cognitively inspired Compositional Theorem Prover that Learns to Prove-a Proposal B Miranda | 4 | 2020 |
| The Curse of Low Task Diversity: On the Failure of Transfer Learning to Outperform MAML and Their Empirical Equivalence B Miranda, P Yu, YX Wang, S Koyejo arXiv preprint arXiv:2208.01545, 2022 | 3 | 2022 |
| An empirical study of the properties of meta-learning-presentation B Miranda | 3 | 2020 |
| 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, 13-19, 2019 | 3 | 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 | 3 | 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 | 3 | 2016 |
TOMASO POGGIOMcDermott Professor in Brain Sciences, MITAdresse e-mail validée de ai.mit.edu
