Mathias Berglund

1.8k total citations
5 papers, 247 citations indexed

About

Mathias Berglund is a scholar working on Computer Vision and Pattern Recognition, Artificial Intelligence and Signal Processing. According to data from OpenAlex, Mathias Berglund has authored 5 papers receiving a total of 247 indexed citations (citations by other indexed papers that have themselves been cited), including 4 papers in Computer Vision and Pattern Recognition, 3 papers in Artificial Intelligence and 2 papers in Signal Processing. Recurrent topics in Mathias Berglund's work include Neural Networks and Applications (2 papers), Music and Audio Processing (2 papers) and Generative Adversarial Networks and Image Synthesis (2 papers). Mathias Berglund is often cited by papers focused on Neural Networks and Applications (2 papers), Music and Audio Processing (2 papers) and Generative Adversarial Networks and Image Synthesis (2 papers). Mathias Berglund collaborates with scholars based in Finland, Switzerland and Canada. Mathias Berglund's co-authors include Tapani Raiko, Klaus Greff, Jelena Luketina, Mikko Honkala, Leo Kärkkäinen, Juha Karhunen, Kyunghyun Cho, Guillaume Alain and Laurent Dinh and has published in prestigious journals such as Neural Networks, arXiv (Cornell University) and Neural Information Processing Systems.

In The Last Decade

Mathias Berglund

5 papers receiving 238 citations

Peers

Mathias Berglund
Yifan Fu Australia
Mathias Berglund
Citations per year, relative to Mathias Berglund Mathias Berglund (= 1×) peers Yifan Fu

Countries citing papers authored by Mathias Berglund

Since Specialization
Citations

This map shows the geographic impact of Mathias Berglund'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 Mathias Berglund with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Mathias Berglund more than expected).

Fields of papers citing papers by Mathias Berglund

Since Specialization
Physical SciencesHealth SciencesLife SciencesSocial Sciences

This network shows the impact of papers produced by Mathias Berglund. 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 Mathias Berglund. The network helps show where Mathias Berglund may publish in the future.

Co-authorship network of co-authors of Mathias Berglund

This figure shows the co-authorship network connecting the top 25 collaborators of Mathias Berglund. A scholar is included among the top collaborators of Mathias Berglund 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 Mathias Berglund. Mathias Berglund is excluded from the visualization to improve readability, since they are connected to all nodes in the network.

All Works

5 of 5 papers shown
1.
Luketina, Jelena, Mathias Berglund, Klaus Greff, & Tapani Raiko. (2016). Scalable gradient-based tuning of continuous regularization hyperparameters. International Conference on Machine Learning. 2952–2960. 22 indexed citations
2.
Luketina, Jelena, Mathias Berglund, Klaus Greff, & Tapani Raiko. (2016). 33rd International Conference on Machine Learning, ICML 2016. International Conference on Machine Learning. 113 indexed citations
3.
Berglund, Mathias, et al.. (2015). Bidirectional recurrent neural networks as generative models. Neural Information Processing Systems. 28. 856–864. 65 indexed citations
4.
Raiko, Tapani, Mathias Berglund, Guillaume Alain, & Laurent Dinh. (2015). Techniques for Learning Binary Stochastic Feedforward Neural Networks. arXiv (Cornell University). 23 indexed citations
5.
Berglund, Mathias, Tapani Raiko, & Kyunghyun Cho. (2014). Measuring the usefulness of hidden units in Boltzmann machines with mutual information. Neural Networks. 64. 12–18. 24 indexed citations

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

Rankless by CCL
2026