James Bergstra

22.5k citations
25 papers · 10.3k · 6 hit papers · h-index 18

Impact in

Papers in

    • Machine Learning and Data Classification 8
    • Neural Networks and Applications 4
    • Computational Physics and Python Applications 4
    • Machine Learning and Algorithms 4
    • Generative Adversarial Networks and Image Synthesis 5
    • Music Technology and Sound Studies 3

James Bergstra

25 papers receiving 9.9k citations

James Bergstra's Hit Papers

Hyperopt: a Python library for model selection and hyperparameter optimization 2015 · 653 citations
6530+6+12Years since publication10002.0k3.0k4.0k5.0k

Peers

James Bergstra
Comparison fields: 5 of 214
  • Artificial Intelligence 4.1k
  • Computer Vision and Pattern Recognition 2.1k
  • Signal Processing 901
  • Environmental Engineering 542
  • Software 141
Replace Tin Kam Ho with:
Tin Kam Ho United States
Kevin P. Murphy Canada
Ben Calderhead United Kingdom
Onur Teymur United Kingdom
Javier Del Ser Spain
Michael Steinbach United States
Jin Wang China
Rich Caruana United States
Paolo Frasconi Italy
Ah Chung Tsoi Australia
James Bergstra relative to Tin Kam Ho United States Tin Kam Ho's profile →
Citations per field
00.5×1.5×
Tin Kam Ho · 1×
Citations per year

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-authors

The 25 scholars most cited alongside James Bergstra, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.

Border = papers with James Bergstra Line = papers co-authored together James Bergstra links everyone, so they are left out of the graph.

All Works

20 of 20 papers shown

Showing the 20 most-cited of 25 papers — load more, or switch the sort, to bring in the rest.

#Work
1
Random search for hyper-parameter optimization
Hit paper breakdown →
20125591
2
Making a Science of Model Search: Hyperparameter Optimization in Hundreds of Dimensions for Vision Architectures
Hit paper breakdown →
2013949
3
Theano: A CPU and GPU Math Compiler in Python
Hit paper breakdown →
2010692
4
An empirical evaluation of deep architectures on problems with many factors of variation
Hit paper breakdown →
2007672
5
Hyperopt: a Python library for model selection and hyperparameter optimization
Hit paper breakdown →
2015653
6
Hyperopt: A Python Library for Optimizing the Hyperparameters of Machine Learning Algorithms
Hit paper breakdown →
2013493
7 2014299
8 2014188
9 2006186
10
Theano: Deep Learning on GPUs with Python
2012126
11
Unsupervised and Transfer Learning Challenge: a Deep Learning Approach
201191
12 201374
13 201242
14
A Spike and Slab Restricted Boltzmann Machine
201141
15
Unsupervised Models of Images by Spike-and-Slab RBMs
201138
16 200935
17
Slow, Decorrelated Features for Pretraining Complex Cell-like Networks
200931
18 201820
19 201417
20 201013

About James Bergstra

James Bergstra is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing, Cognitive Neuroscience and Computational Theory and Mathematics, having authored 25 papers that have together received 10.3k indexed citations. Recurring topics across this work include Machine Learning and Data Classification (8 papers), Music and Audio Processing (6 papers), Generative Adversarial Networks and Image Synthesis (5 papers), Neural dynamics and brain function (4 papers), Neural Networks and Applications (4 papers), Computational Physics and Python Applications (4 papers), Machine Learning and Algorithms (4 papers) and Music Technology and Sound Studies (3 papers). The work is most often cited by research in Artificial Intelligence (4.1k citations), Computer Vision and Pattern Recognition (2.1k citations), Signal Processing (901 citations), Environmental Engineering (542 citations) and Software (141 citations). James Bergstra has collaborated with scholars based in Canada, United States and France. Frequent co-authors include Yoshua Bengio, David Cox, Daniel Yamins, Dan Yamins, Chris Eliasmith, Brent Komer, Dumitru Erhan, Aaron Courville, Hugo Larochelle and Guillaume Desjardins. Their work appears in journals such as Machine Learning, IEEE Transactions on Pattern Analysis and Machine Intelligence, Frontiers in Neuroinformatics, Cognitive Science and Neural Computation.

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