Pierre Baldi
Artificial Intelligence · 1988–2023
A researcher in the Science corpus: 76 papers; trusts 1,191 researchers and is trusted by 1,968 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 373 citations into it; #829 of 36,961 by trust here, #1,915 by citations
- Nuclear and High Energy Physics — 266 citations into it; #1,186 of 6,167 by trust here, #1,687 by citations
- Molecular Biology — 261 citations into it; #118 of 17,836 by trust here, #689 by citations
- Computer Vision and Pattern Recognition — 170 citations into it; #2,003 of 21,973 by trust here, #2,313 by citations
- Computational Biology & Bioinformatics — 94 citations into it; #140 of 661 by trust here, #248 by citations
- Computational Theory and Mathematics — 87 citations into it; #589 of 12,489 by trust here, #284 by citations
- Materials Chemistry — 77 citations into it; #300 of 11,531 by trust here, #2,492 by citations
- Model Architectures — 73 citations into it; #209 of 2,288 by trust here, #447 by citations
Whom Pierre Baldi trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Yoshua Bengio
- Alex Krizhevsky
- Yann LeCun
- Radford M. Neal
- Ilya Sutskever
- Diederik P. Kingma
- Christopher K. I. Williams
- Laurent Itti
- Gianluca Pollastri
Who trusts Pierre Baldi overall
- J. Urgen Schmidhuber
- Jianlin Cheng
- Yoshua Bengio
- Kenji Kawaguchi
- Kyunghyun Cho
- Gianluca Pollastri
- Thomas G. Dietterich
- Peter Sadowski
- David Lopez-Paz
- Zachary Chase Lipton
Papers from Pierre Baldi's perspective
Ordered by how strongly the researchers Pierre Baldi 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)
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- 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
- Neural networks and principal component analysis: Learning from examples without local minima (1989)
- Bayesian surprise attracts human attention (2005) — 1,751 citations
- Understanding Dropout (2013) — 785 citations
- Searching for exotic particles in high-energy physics with deep learning (2014) — 1,320 citations
- Language Models can Solve Computer Tasks (2023) — 522 citations
- A principled approach to detecting surprising events in video (2005) — 435 citations
- The dropout learning algorithm (2014) — 343 citations
- Learning Activation Functions to Improve Deep Neural Networks (2014) — 512 citations
- Learning in the Machine: Random Backpropagation and the Deep Learning Channel (2016) — 72 citations
- Learning in linear neural networks: a survey (1995)
- Deep architectures for protein contact map prediction (2012) — 286 citations
- Of Bits and Wows: A Bayesian Theory of Surprise with Applications to Attention (2009) — 310 citations
- Learning to play Go using recursive neural networks (2008) — 32 citations
- Complex-Valued Autoencoders (2011) — 63 citations
- Prediction of contact maps by GIOHMMs and recurrent neural networks using lateral propagation from all four cardinal corners (2002) — 156 citations
- Solving the Rubik’s cube with deep reinforcement learning and search (2019) — 210 citations
- Assessing the accuracy of prediction algorithms for classification: an overview (2000) — 2,199 citations
- Temporal Evolution of Generalization during Learning in Linear Networks (1991)
- Improving the prediction of protein secondary structure in three and eight classes using recurrent neural networks and profiles (2002) — 809 citations
- Deep architectures and deep learning in chemoinformatics: the prediction of aqueous solubility for drug-like molecules (2013) — 506 citations