Alessandro Achille
Artificial Intelligence · 2016–2021
A researcher in the Science corpus: 21 papers; trusts 1,522 researchers and is trusted by 405 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 462 citations into it; #2,338 of 36,961 by trust here, #2,747 by citations
- Computer Vision and Pattern Recognition — 224 citations into it; #2,820 of 21,973 by trust here, #2,566 by citations
- Optimization & Training — 118 citations into it; #702 of 2,605 by trust here, #738 by citations
- Representation & Self-Supervised Learning — 82 citations into it; #549 of 3,156 by trust here, #607 by citations
- Natural Language Processing — 50 citations into it
- Scaling & Learning Theory — 45 citations into it; #241 of 429 by trust here, #289 by citations
- Model Architectures — 44 citations into it
- Cognitive Neuroscience — 42 citations into it; #5,162 of 11,026 by trust here, #7,047 by citations
Whom Alessandro Achille trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Alex Krizhevsky
- Yann LeCun
- Geoffrey E. Hinton
- Yoshua Bengio
- Kaiming He
- James Martens
- Stefano Soatto
- Naftali Tishby
- Ilya Sutskever
Who trusts Alessandro Achille overall
- Stefano Soatto
- Aditya Golatkar
- Shuyang Gao
- Pratik Chaudhari
- Fei Ye
- T. Chen
- Daniel Moyer
- Haohan Wang
- Gintare Karolina Dziugaite
- Greg Ver Steeg
Papers from Alessandro Achille's perspective
Ordered by how strongly the researchers Alessandro Achille trusts endorse each paper. Same corpus, a different order for every researcher.
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Attention is All you Need (Neural Information Processing Systems)
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Learning Multiple Layers of Features from Tiny Images
- ImageNet Large Scale Visual Recognition Challenge
Their papers
- Emergence of Invariance and Disentanglement in Deep Representations (2017) — 566 citations
- Information Dropout: Learning Optimal Representations Through Noisy Computation (2016) — 462 citations
- Task2Vec: Task Embedding for Meta-Learning (2019) — 377 citations
- Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies (2018) — 136 citations
- Toward Understanding Catastrophic Forgetting in Continual Learning (2019) — 124 citations
- Critical Learning Periods in Deep Neural Networks (2017) — 124 citations
- Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks (2019) — 845 citations
- Mixed-Privacy Forgetting in Deep Networks (2020) — 233 citations
- Time Matters in Regularizing Deep Networks: Weight Decay and Data Augmentation Affect Early Learning Dynamics, Matter Little Near Convergence (2019) — 110 citations
- Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations (2020) — 257 citations
- Structured Prediction as Translation between Augmented Natural Languages (2021) — 364 citations
- Where is the Information in a Deep Neural Network? (2019) — 97 citations
- The Information Complexity of Learning Tasks, their Structure and their Distance (2019) — 61 citations
- Critical Learning Periods in Deep Networks (2018) — 169 citations
- A Separation Principle for Control in the Age of Deep Learning (2017) — 33 citations
- LQF: Linear Quadratic Fine-Tuning (2020) — 33 citations
- Incremental Meta-Learning via Indirect Discriminant Alignment (2020) — 6 citations
- Where is the Information in a Deep Network (2019)
- The Dynamics of Differential Learning I: Information-Dynamics and Task Reachability (2018) — 7 citations
- Information Dropout: learning optimal representations through noise (2017) — 27 citations