Alexandre Lacoste
Artificial Intelligence · 2014–2021
A researcher in the Science corpus: 18 papers; trusts 1,402 researchers and is trusted by 815 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 522 citations into it; #1,931 of 36,961 by trust here, #2,326 by citations
- Computer Vision and Pattern Recognition — 234 citations into it; #2,136 of 21,973 by trust here, #2,544 by citations
- Representation & Self-Supervised Learning — 116 citations into it; #507 of 3,156 by trust here, #812 by citations
- Probabilistic & Bayesian Methods — 104 citations into it; #1,316 of 1,526 by trust here, #751 by citations
- Natural Language Processing — 69 citations into it; #5,157 of 5,725 by trust here, #2,184 by citations
- Statistics and Probability — 68 citations into it
- Management Science and Operations Research — 57 citations into it
- Optimization & Training — 54 citations into it; #1,749 of 2,605 by trust here, #2,262 by citations
Whom Alexandre Lacoste trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Diederik P. Kingma
- Geoffrey E. Hinton
- Yoshua Bengio
- Kaiming He
- Alex Krizhevsky
- Yann LeCun
- Jimmy Ba
- Ilya Sutskever
- Alex Graves
- Hugo Larochelle
Who trusts Alexandre Lacoste overall
- Han-Jia Ye
- Fabian Pedregosa
- Gang Luo
- Aimee van Wynsberghe
- Marc-André Zöller
- Anne-Laure Ligozat
- Chelsea Finn
- David A. Patterson
- Alexandra Sasha Luccioni
- Sebastian Flennerhag
Papers from Alexandre Lacoste's perspective
Ordered by how strongly the researchers Alexandre Lacoste 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)
- Long Short-Term Memory
- Attention is All you Need (Neural Information Processing Systems)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- 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
- TADAM: Task dependent adaptive metric for improved few-shot learning (2018) — 1,482 citations
- WikiReading: A Novel Large-scale Language Understanding Task over Wikipedia (2016) — 146 citations
- Quantifying the Carbon Emissions of Machine Learning (2019) — 970 citations
- Coarse-to-Fine Question Answering for Long Documents (2016) — 170 citations
- Neural Autoregressive Flows (2018) — 495 citations
- Bayesian Hypernetworks (2017) — 157 citations
- Uncertainty in Multitask Transfer Learning (2018) — 21 citations
- Deep Prior (2017) — 7 citations
- Learning Heuristics for the TSP by Policy Gradient (2018) — 381 citations
- Variational Causal Networks: Approximate Bayesian Inference over Causal Structures (2021) — 61 citations
- PAC-Bayesian Theory Meets Bayesian Inference (2016) — 214 citations
- Tackling Climate Change with Machine Learning (2019) — 1,184 citations
- Differentiable Causal Discovery from Interventional Data (2020) — 282 citations
- Online Fast Adaptation and Knowledge Accumulation (OSAKA): a New Approach to Continual Learning (2020) — 80 citations
- Adaptive Deep Kernel Learning (2019) — 31 citations
- Sequential Model-Based Ensemble Optimization (2014) — 37 citations
- Seasonal Contrast: Unsupervised Pre-Training from Uncurated Remote Sensing Data (2021) — 383 citations
- Disentanglement via Mechanism Sparsity Regularization: A New Principle for Nonlinear ICA (2021) — 190 citations