James Bergstra
Artificial Intelligence · 2006–2018
A researcher in the Science corpus: 20 papers; trusts 551 researchers and is trusted by 8,330 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 158 citations into it; #173 of 36,961 by trust here, #381 by citations
- Computer Vision and Pattern Recognition — 106 citations into it; #880 of 21,973 by trust here, #1,690 by citations
- Optimization & Training — 42 citations into it; #51 of 2,605 by trust here, #78 by citations
- Representation & Self-Supervised Learning — 41 citations into it; #755 of 3,156 by trust here, #448 by citations
- Probabilistic & Bayesian Methods — 32 citations into it; #601 of 1,526 by trust here, #904 by citations
- Evaluation & Benchmarks — 30 citations into it; #913 of 3,155 by trust here, #327 by citations
- Model Architectures — 28 citations into it
- Computational Theory and Mathematics — 23 citations into it; #855 of 12,489 by trust here, #74 by citations
Whom James Bergstra trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Geoffrey E. Hinton
- Alex Krizhevsky
- Frank Hutter
- Yoshua Bengio
- Leo Breiman
- Yann LeCun
- Hugo Larochelle
- Adam Coates
- Radford M. Neal
- Andrew Y. Ng
Who trusts James Bergstra overall
- Yoshua Bengio
- Frank Hutter
- Katharina Eggensperger
- Aaron Klein
- Martin Wistuba
- Matthias Feurer
- Quoc V. Le
- Kyunghyun Cho
- Barret Zoph
- Jitendra Malik
Papers from James Bergstra's perspective
Ordered by how strongly the researchers James Bergstra trusts endorse each paper. Same corpus, a different order for every researcher.
- ImageNet classification with deep convolutional neural networks
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Gradient-based learning applied to document recognition
- Attention is All you Need (Neural Information Processing Systems)
- Long Short-Term Memory
- ImageNet: A large-scale hierarchical image database
- Learning Multiple Layers of Features from Tiny Images
- Very Deep Convolutional Networks for Large-Scale Image Recognition (International Conference on Learning Representations)
- Going deeper with convolutions
Their papers
- Random Search for Hyper-Parameter Optimization (2012) — 11,272 citations
- Algorithms for Hyper-Parameter Optimization (2011) — 5,706 citations
- An empirical evaluation of deep architectures on problems with many factors of variation (2007) — 1,201 citations
- Theano: A Python framework for fast computation of mathematical expressions (2016) — 2,380 citations
- Pylearn2: a machine learning research library (2013) — 305 citations
- Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures (2013) — 2,576 citations
- Theano: A CPU and GPU Math Compiler in Python (2010) — 862 citations
- A Spike and Slab Restricted Boltzmann Machine (2011) — 101 citations
- Challenges in representation learning: A report on three machine learning contests (2013) — 2,020 citations
- Unsupervised Models of Images by Spikeand-Slab RBMs (2011) — 81 citations
- Theano: Deep Learning on GPUs with Python (2012) — 280 citations
- Benchmarking Reinforcement Learning Algorithms on Real-World Robots (2018) — 189 citations
- Hyperopt-Sklearn: Automatic Hyperparameter Configuration for Scikit-Learn (2014) — 317 citations
- Hyperopt: a Python library for model selection and hyperparameter optimization (2015) — 963 citations
- Aggregate features and ADABOOST for music classification (2006) — 328 citations
- Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms (2013) — 808 citations
- Theano: new features and speed improvements (2012) — 1,415 citations
- Nengo: a Python tool for building large-scale functional brain models (2014) — 507 citations
- Hyperparameter Optimization and Boosting for Classifying Facial Expressions: How good can a "Null" Model be? (2013) — 23 citations
- Unsupervised and Transfer Learning Challenge: a Deep Learning Approach (2011) — 241 citations