Soham De
Impact in
-
- Advanced Neural Network Applications
- Generative Adversarial Networks and Image Synthesis
- Artificial Intelligence top 10%
- Stochastic Gradient Optimization Techniques
- Adversarial Robustness in Machine Learning
- Domain Adaptation and Few-Shot Learning
- Anomaly Detection Techniques and Applications
- Machine Learning and ELM
Papers in
-
- Stochastic Gradient Optimization Techniques 5
- Adversarial Robustness in Machine Learning 5
- Machine Learning and Data Classification 3
- Machine Learning and Algorithms 2
-
- Advanced Neural Network Applications 4
- Co-authors
- Tom Goldstein (4 shared papers)Samuel Smith (5 shared papers)Zheng Xu (2 shared papers)Christoph Studer (1 shared paper)Hanan Samet (1 shared paper)Hao Li (1 shared paper)David W. Jacobs (1 shared paper)David G. T. Barrett (1 shared paper)
- Journals
- Scientific Reports (1 paper)Langmuir (1 paper)Uncertainty in Artificial Intelligence (1 paper)arXiv (Cornell University) (4 papers)Zenodo (CERN European Organization for Nuclear Research) (1 paper)
- Partner nations
- United StatesIndiaUnited Kingdom
In The Last Decade
Soham De
22 papers receiving 225 citations
Peers
Comparison fields: 5 of 78
- Computer Vision and Pattern Recognition 92
- Artificial Intelligence 139
- Computer Graphics and Computer-Aided Design 6
- Computational Mathematics 1
- Computational Mechanics 32
Countries citing papers authored by Soham De
This map shows the geographic impact of Soham De'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 Soham De with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Soham De more than expected).
Fields of papers citing papers by Soham De
This network shows the impact of papers produced by Soham De. 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 Soham De. The network helps show where Soham De may publish in the future.
Co-authors
The 25 scholars most cited alongside Soham De, linked wherever they have co-authored with each other. Click a name or a connecting line to browse the papers they share.
All Works
Showing the 20 most-cited of 22 papers — load more, or switch the sort, to bring in the rest.
| # | Work | ||
|---|---|---|---|
| 1 | Training Quantized Nets: A Deeper Understanding | 2017 | 37 |
| 2 | Adversarial Robustness through Local Linearization | 2019 | 27 |
| 3 | 2017 | 25 | |
| 4 | Automated Inference with Adaptive Batches | 2017 | 23 |
| 5 | 2016 | 20 | |
| 6 | 2021 | 19 | |
| 7 | 2015 | 17 | |
| 8 | Convergence guarantees for RMSProp and ADAM in non-convex optimization and their comparison to Nesterov acceleration on autoencoders. | 2018 | 16 |
| 9 | 2020 | 11 | |
| 10 | Efficient Neural Network Verification with Exactness Characterization | 2019 | 8 |
| 11 | 2011 | 6 | |
| 12 | 2016 | 5 | |
| 13 | iAnon: Leveraging Social Network Big Data to Mitigate Behavioral Symptoms of Cyberbullying | 2014 | 4 |
| 14 | 2022 | 4 | |
| 15 | Batch Normalization Biases Deep Residual Networks Towards Shallow Paths | 2020 | 3 |
| 16 | Batch Normalization Biases Residual Blocks Towards the Identity Function in Deep Networks | 2020 | 3 |
| 17 | 2025 | 3 | |
| 18 | 2012 | 2 | |
| 19 | 2016 | 2 | |
| 20 | Batch Normalization has Multiple Benefits: An Empirical Study on Residual Networks | 2019 | 1 |
About Soham De
Soham De is a scholar working on Artificial Intelligence, Computer Vision and Pattern Recognition, Sociology and Political Science, Communication and Statistical and Nonlinear Physics, having authored 22 papers that have together received 238 indexed citations. Recurring topics across this work include Stochastic Gradient Optimization Techniques (5 papers), Adversarial Robustness in Machine Learning (5 papers), Advanced Neural Network Applications (4 papers), Social Media and Politics (3 papers), Machine Learning and Data Classification (3 papers), Model Reduction and Neural Networks (3 papers), Machine Learning and Algorithms (2 papers) and Misinformation and Its Impacts (2 papers). The work is most often cited by research in Computer Vision and Pattern Recognition (92 citations), Artificial Intelligence (139 citations), Computer Graphics and Computer-Aided Design (6 citations), Computational Mathematics (1 citation) and Computational Mechanics (32 citations). Soham De has collaborated with scholars based in United States, India and United Kingdom. Frequent co-authors include Tom Goldstein, Samuel Smith, Zheng Xu, Christoph Studer, Hanan Samet, Hao Li, David W. Jacobs, David G. T. Barrett, Michele J. Gelfand and Patrick Roos. Their work appears in journals such as Scientific Reports, Langmuir, Uncertainty in Artificial Intelligence, arXiv (Cornell University) and Zenodo (CERN European Organization for Nuclear Research).
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.