| Emergence of invariance and disentanglement in deep representations A Achille, S Soatto The Journal of Machine Learning Research 19 (1), 1947-1980, 2018 | 191 | 2018 |
| Information Dropout: Learning optimal representations through noisy computation A Achille, S Soatto IEEE Transactions on Pattern Analysis and Machine Intelligence 40 (12), 2897 …, 2018 | 162* | 2018 |
| Life-long disentangled representation learning with cross-domain latent homologies A Achille, T Eccles, L Matthey, C Burgess, N Watters, A Lerchner, ... Advances in Neural Information Processing Systems, 9873-9883, 2018 | 30 | 2018 |
| Task2vec: Task embedding for meta-learning A Achille, M Lam, R Tewari, A Ravichandran, S Maji, CC Fowlkes, ... Proceedings of the IEEE International Conference on Computer Vision, 6430-6439, 2019 | 28 | 2019 |
| Critical Learning Periods in Deep Networks A Achille, M Rovere, S Soatto International Conference on Learning Representations, 2019 | 26* | 2019 |
| A separation principle for control in the age of deep learning A Achille, S Soatto Annual Review of Control, Robotics, and Autonomous Systems 1, 287-307, 2018 | 9 | 2018 |
| Where is the information in a deep neural network? A Achille, S Soatto ArXiv Preprints, arXiv:1905.12213 1905 (12213), 1-13, 2019 | 7* | 2019 |
| The information complexity of learning tasks, their structure and their distance A Achille, G Paolini, G Mbeng, S Soatto arXiv preprint arXiv:1904.03292, 2019 | 6 | 2019 |
| The Dynamic Distance Between Learning Tasks A Achille, GB Mbeng, S Soatto | 5* | 2018 |
| Toward understanding catastrophic forgetting in continual learning CV Nguyen, A Achille, M Lam, T Hassner, V Mahadevan, S Soatto arXiv preprint arXiv:1908.01091, 2019 | 4 | 2019 |
| E46K-like α-synuclein mutants increase lipid interactions and disrupt membrane selectivity M Rovere, AE Powers, H Jiang, JC Pitino, L Fonseca-Ornelas, DS Patel, ... Journal of Biological Chemistry 294 (25), 9799-9812, 2019 | 3 | 2019 |
| Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence AS Golatkar, A Achille, S Soatto Advances in Neural Information Processing Systems, 10677-10687, 2019 | 2 | 2019 |
| Information complexity of tasks, their structure and their distance A Achille, G Mbeng, G Paolini, S Soatto Technical Report UCLA CSD: 180003, Department of Computer Science …, 2018 | 2 | 2018 |
| Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations A Golatkar, A Achille, S Soatto arXiv preprint arXiv:2003.02960, 2020 | 1 | 2020 |
| Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Neural Networks A Golatkar, A Achille, S Soatto The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 | 1* | 2019 |
| A Vietoris–Smale mapping theorem for the homotopy of hyperdefinable sets A Achille, A Berarducci Selecta Mathematica 24 (4), 3445-3473, 2018 | 1 | 2018 |
| TextTubes for Detecting Curved Text in the Wild J Seytre, J Wu, A Achille arXiv preprint arXiv:1912.08990, 2019 | | 2019 |
| Emergent Properties of Deep Neural Networks A Achille UCLA, 2019 | | 2019 |
| Dynamics and Reachability of Learning Tasks A Achille, G Mbeng, S Soatto arXiv preprint arXiv:1810.02440, 2018 | | 2018 |
| Groups definable in o-minimal and NIP settings A Achille University of Pisa, 2015 | | 2015 |
Stefano SoattoProfessor of Computer Science, UCLAVerified email at ucla.edu
