James Bergstra

22.3k total citations · 6 hit papers
25 papers, 10.1k citations indexed

About

James Bergstra is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition and Signal Processing. According to data from OpenAlex, James Bergstra has authored 25 papers receiving a total of 10.1k indexed citations (citations by other indexed papers that have themselves been cited), including 16 papers in Artificial Intelligence, 10 papers in Computer Vision and Pattern Recognition and 6 papers in Signal Processing. Recurrent topics in James Bergstra's work include Machine Learning and Data Classification (8 papers), Music and Audio Processing (6 papers) and Generative Adversarial Networks and Image Synthesis (5 papers). James Bergstra is often cited by papers focused on Machine Learning and Data Classification (8 papers), Music and Audio Processing (6 papers) and Generative Adversarial Networks and Image Synthesis (5 papers). James Bergstra collaborates with scholars based in Canada, United States and France. James Bergstra's co-authors include Yoshua Bengio, David Cox, Daniel Yamins, Dan Yamins, Chris Eliasmith, Brent Komer, Aaron Courville, Dumitru Erhan, Hugo Larochelle and Guillaume Desjardins and has published in prestigious journals such as IEEE Transactions on Pattern Analysis and Machine Intelligence, Neural Computation and Machine Learning.

In The Last Decade

James Bergstra

25 papers receiving 9.7k citations

Hit Papers

5 papers align trajectories

What are hit papers?

Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the same subfield and year (this is the minimum needed to enter the top 1%, not the average within it), or reaches the top citation threshold in at least one of its specific research topics.

Random search for hyper-parameter optimization

2012 5.5k citations James Bergstra, Yoshua Bengio profile →
Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures

2013 935 citations James Bergstra, Daniel Yamins et al. Digital Access to Scholarship at Harvard (DASH) (Harvard University) profile →
Theano: A CPU and GPU Math Compiler in Python

2010 686 citations James Bergstra, Olivier Breuleux et al. Proceedings of the Python in Science Conferences profile →
An empirical evaluation of deep architectures on problems with many factors of variation

2007 665 citations Hugo Larochelle, Dumitru Erhan et al. profile →
Hyperopt: a Python library for model selection and hyperparameter optimization

2015 636 citations James Bergstra, Brent Komer et al. profile →
Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms

2013 485 citations James Bergstra, Dan Yamins et al. Proceedings of the Python in Science Conferences profile →

Peers

Countries citing papers authored by James Bergstra

Since Specialization

Citations

This map shows the geographic impact of James Bergstra's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by James Bergstra with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites James Bergstra more than expected).

Fields of papers citing papers by James Bergstra

Since Specialization

Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by James Bergstra. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by James Bergstra. The network helps show where James Bergstra may publish in the future.

Co-authorship network of co-authors of James Bergstra

This figure shows the co-authorship network connecting the top 25 collaborators of James Bergstra. A scholar is included among the top collaborators of James Bergstra based on the total number of citations received by their joint publications. Widths of edges represent the number of papers authors have co-authored together. Node borders signify the number of papers an author published with James Bergstra. James Bergstra is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

Sort: Min cites: Since: Top N: Style:

20 of 20 papers shown

#	Work	Indexed citations
1	Benchmarking Reinforcement Learning Algorithms on Real-World Robots 2018 ·arXiv (Cornell University) ·(unknown), Dmytro Korenkevych, (unknown), (unknown), James Bergstra	19
2	SkData: data sets and algorithm evaluation protocols in Python 2015 ·James Bergstra, Nicolas Pinto, David Cox	1
3	Nengo: a Python tool for building large-scale functional brain models 2014 ·Frontiers in Neuroinformatics ·Trevor Bekolay, James Bergstra, Eric Hunsberger, Travis DeWolf, Terrence C. Stewart, Daniel Rasmussen, Xuan Choo, Aaron R. Voelker, Chris Eliasmith	292
4	Preface 2014 ·Proceedings of the Python in Science Conferences ·Andy R. Terrel, Jonathan Rocher, (unknown), James Bergstra	1
5	Hyperopt-Sklearn: Automatic Hyperparameter Configuration for Scikit-Learn 2014 ·Proceedings of the Python in Science Conferences ·Brent Komer, James Bergstra, Chris Eliasmith	187
6	A Neural Model of Human Image Categorization 2013 ·Cognitive Science ·Eric Hunsberger, Peter Blouw, James Bergstra, Chris Eliasmith	2
7	Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures breakdown → 2013 ·Digital Access to Scholarship at Harvard (DASH) (Harvard University) ·James Bergstra, Daniel Yamins, David Cox	935
8	Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms breakdown → 2013 ·Proceedings of the Python in Science Conferences ·James Bergstra, Dan Yamins, David Cox	485
9	SkData: Data Sets and Algorithm Evaluation Protocols in Python 2013 ·Proceedings of the Python in Science Conferences ·James Bergstra, Nicolas Pinto, D. J. Cox	73
10	Machine learning for predictive auto-tuning with boosted regression trees 2012 ·Digital Access to Scholarship at Harvard (DASH) (Harvard University) ·James Bergstra, Nicolas Pinto, David Cox	41
11	Random search for hyper-parameter optimization breakdown → 2012 ·James Bergstra, Yoshua Bengio	5520
12	Unsupervised Models of Images by Spike-and-Slab RBMs 2011 ·International Conference on Machine Learning ·Yoshua Bengio, Aaron Courville, James Bergstra	38
13	A Spike and Slab Restricted Boltzmann Machine 2011 ·International Conference on Artificial Intelligence and Statistics ·Aaron Courville, James Bergstra, Yoshua Bengio	41
14	Unsupervised and Transfer Learning Challenge: a Deep Learning Approach 2011 ·International Conference on Machine Learning ·Grégoire Mesnil, Yann Dauphin, Xavier Glorot, Salah Rifai, Yoshua Bengio, Ian Goodfellow, (unknown), Xavier Muller, Guillaume Desjardins, David Warde-Farley, Pascal Vincent, Aaron Courville, James Bergstra	90
15	Theano: A CPU and GPU Math Compiler in Python breakdown → 2010 ·Proceedings of the Python in Science Conferences ·James Bergstra, Olivier Breuleux, Frédéric Bastien, Pascal Lamblin, Razvan Pascanu, Guillaume Desjardins, Joseph Turian, David Warde-Farley, Yoshua Bengio	686
16	Scalable Genre And Tag Prediction With Spectral Covariance. 2010 ·Zenodo (CERN European Organization for Nuclear Research) ·James Bergstra, Michael Mandel, Douglas Eck	13
17	Slow, Decorrelated Features for Pretraining Complex Cell-like Networks 2009 ·Neural Information Processing Systems ·Yoshua Bengio, James Bergstra	31
18	Quadratic features and deep architectures for chunking 2009 ·Joseph Turian, James Bergstra, Yoshua Bengio	35
19	An empirical evaluation of deep architectures on problems with many factors of variation breakdown → 2007 ·Hugo Larochelle, Dumitru Erhan, Aaron Courville, James Bergstra, Yoshua Bengio	665
20	Aggregate features and ADABOOST for music classification 2006 ·Machine Learning ·James Bergstra, Norman Casagrande, Dumitru Erhan, Douglas Eck, Balázs Kégl	183

Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive bibliographic database. While OpenAlex provides broad and valuable coverage of the global research landscape, it—like all bibliographic datasets—has inherent limitations. These include incomplete records, variations in author disambiguation, differences in journal indexing, and delays in data updates. As a result, some metrics and network relationships displayed in Rankless may not fully capture the entirety of a scholar's output or impact.

Explore authors with similar magnitude of impact