Salah Rifai
- Artificial Intelligence top 2%
- Computer Vision and Pattern Recognition top 2%
- Signal Processing top 5%
- Control and Systems Engineering top 10%
- Computer Networks and Communications
- Co-authors
- Yoshua BengioPascal VincentXavier MullerXavier GlorotYann DauphinAaron CourvilleJames BergstraDavid Warde-Farley
- Topics
- Neural Networks and Applications (4 papers)Generative Adversarial Networks and Image Synthesis (4 papers)Model Reduction and Neural Networks (3 papers)
- Journals
- arXiv (Cornell University)Neural Information Processing SystemsInternational Conference on Machine Learning
In The Last Decade
Salah Rifai
7 papers receiving 890 citations
Hit Papers
Peers
Comparison fields: 5 of 101
- Artificial Intelligence 541
- Computer Vision and Pattern Recognition 462
- Signal Processing 130
- Control and Systems Engineering 69
- Computer Networks and Communications 51
Countries citing papers authored by Salah Rifai
This map shows the geographic impact of Salah Rifai'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 Salah Rifai with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Salah Rifai more than expected).
Fields of papers citing papers by Salah Rifai
This network shows the impact of papers produced by Salah Rifai. 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 Salah Rifai. The network helps show where Salah Rifai may publish in the future.
Co-authorship network of co-authors of Salah Rifai
This figure shows the co-authorship network connecting the top 25 collaborators of Salah Rifai. A scholar is included among the top collaborators of Salah Rifai 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 Salah Rifai. Salah Rifai is excluded from the visualization to improve readability, since they are connected to all nodes in the network.
All Works
| # | Work | Indexed citations |
|---|---|---|
| 1 | A Generative Process for Contractive Auto-Encoders. | 3 |
| 2 | Regularized Auto-Encoders Estimate Local Statistics | 3 |
| 3 | 21 | |
| 4 | Contractive Auto-Encoders: Explicit Invariance During Feature Extractionbreakdown → | 675 |
| 5 | The Manifold Tangent Classifier | 87 |
| 6 | Unsupervised and Transfer Learning Challenge: a Deep Learning Approach | 90 |
| 7 | Deep Learners Benefit More from Out-of-Distribution Examples | 52 |
About Salah Rifai
Salah Rifai is a scholar working on Computer Vision and Pattern Recognition, Statistical and Nonlinear Physics and Artificial Intelligence, having authored 7 papers that have together received 931 indexed citations. Recurring topics across this work include Neural Networks and Applications (4 papers), Generative Adversarial Networks and Image Synthesis (4 papers) and Model Reduction and Neural Networks (3 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (462 citations), Artificial Intelligence (541 citations) and Signal Processing (130 citations). Salah Rifai has collaborated with scholars based in Canada, France and Germany. Frequent co-authors include Yoshua Bengio, Pascal Vincent, Xavier Muller, Xavier Glorot, Yann Dauphin, Aaron Courville, James Bergstra, David Warde-Farley, Grégoire Mesnil and Guillaume Desjardins. Their work appears in journals such as arXiv (Cornell University), Neural Information Processing Systems and International Conference on Machine Learning.
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.