Prashant Singh
Associate senior lecturer/Assistant Professor at Department of Information Technology; Division of Scientific Computing
- Telephone:
- +46 18 471 54 12
- E-mail:
- prashant.singh@it.uu.se
- Visiting address:
- Hus 10, Regementsvägen 10
- Postal address:
- Box 337
751 05 UPPSALA
- Academic merits:
- Docent
Short presentation
Prashant Singh is an Assistant Professor, Docent at the Division of Scientific Computing, Department of Information Technology. He is also affiliated to the Science for Life Laboratory, Uppsala University as a SciLifeLab fellow. His research interests involve developing machine learning and optimization methods to enable fast, data-efficient analysis and processing of scientific data, particularly in the domain of life sciences.
Keywords
- scientific computing
- systems biology
- machine learning
- optimization
- active learning
- bayesian inference
- surrogate models
Biography
Prior to joining Uppsala University, Prashant Singh was an Assistant Professor at the Department of Computing Science, Umeå University. Prashant was a postdoctoral researcher at the Division of Scientific Computing, Department of Information Technology, Uppsala University between 2017 and 2020, where his research explored machine learning and statistical sampling methods within the domain of computational biology. Prashant Singh obtained the degree of PhD in Computer Science Engineering from Ghent University, Belgium in May 2016, where he specialized in model-based optimization and active learning. Prashant received his MSc degree in Computer Science from the University of Delhi, India in 2011, with specialization in data mining and supervised machine learning.
Research
Prashant's research interests broadly span optimization and machine learning. He is particularly interested in developing efficient methods for data-scarce or computationally expensive problems. Some related topics include constrained multi-objective optimization, surrogate modeling, parameter inference, inverse modeling, active learning, sequential sampling, design of experiments, etc.
Publications
Recent publications
Bayesian polynomial neural networks and polynomial neural ordinary differential equations
Part of PloS Computational Biology, 2024
- DOI for Bayesian polynomial neural networks and polynomial neural ordinary differential equations
- Download full text (pdf) of Bayesian polynomial neural networks and polynomial neural ordinary differential equations
Adaptive Robust Learning using Latent Bernoulli Variables
Part of Proceedings of the 41st International Conference on Machine Learning, p. 23105-23122, 2024
Transfer Learning-Assisted Inverse Modeling in Nanophotonics Based on Mixture Density Networks
Part of IEEE Access, p. 55218-55224, 2024
- DOI for Transfer Learning-Assisted Inverse Modeling in Nanophotonics Based on Mixture Density Networks
- Download full text (pdf) of Transfer Learning-Assisted Inverse Modeling in Nanophotonics Based on Mixture Density Networks
Efficient Resource Scheduling for Distributed Infrastructures using Negotiation Capabilities
Part of 2023 IEEE 16th International Conference on Cloud Computing (CLOUD), p. 486-492, 2023
To test, or not to test: A proactive approach for deciding complete performance test initiation
Part of BIG-DATA 2022, p. 4758-4767, 2022
All publications
Articles in journal
Bayesian polynomial neural networks and polynomial neural ordinary differential equations
Part of PloS Computational Biology, 2024
- DOI for Bayesian polynomial neural networks and polynomial neural ordinary differential equations
- Download full text (pdf) of Bayesian polynomial neural networks and polynomial neural ordinary differential equations
Transfer Learning-Assisted Inverse Modeling in Nanophotonics Based on Mixture Density Networks
Part of IEEE Access, p. 55218-55224, 2024
- DOI for Transfer Learning-Assisted Inverse Modeling in Nanophotonics Based on Mixture Density Networks
- Download full text (pdf) of Transfer Learning-Assisted Inverse Modeling in Nanophotonics Based on Mixture Density Networks
Identification of dynamic mass-action biochemical reaction networks using sparse Bayesian methods
Part of PloS Computational Biology, 2022
- DOI for Identification of dynamic mass-action biochemical reaction networks using sparse Bayesian methods
- Download full text (pdf) of Identification of dynamic mass-action biochemical reaction networks using sparse Bayesian methods
Convolutional Neural Networks as Summary Statistics for Approximate Bayesian Computation
Part of IEEE/ACM Transactions on Computational Biology & Bioinformatics, p. 3353-3365, 2022
Part of PloS Computational Biology, 2022
- DOI for Systematic comparison of modeling fidelity levels and parameter inference settings applied to negative feedback gene regulation
- Download full text (pdf) of Systematic comparison of modeling fidelity levels and parameter inference settings applied to negative feedback gene regulation
Part of BMC Bioinformatics, 2021
- DOI for Accelerated regression-based summary statistics for discrete stochastic systems via approximate simulators
- Download full text (pdf) of Accelerated regression-based summary statistics for discrete stochastic systems via approximate simulators
Scalable machine learning-assisted model exploration and inference using Sciope
Part of Bioinformatics, p. 279-281, 2021
- DOI for Scalable machine learning-assisted model exploration and inference using Sciope
- Download full text (pdf) of Scalable machine learning-assisted model exploration and inference using Sciope
Epidemiological modeling in StochSS Live!
Part of Bioinformatics, p. 2787-2788, 2021
Part of Journal of Optimization Theory and Applications, p. 172-193, 2017
Constrained multi-objective antenna design optimization using surrogates
Part of International journal of numerical modelling, 2017
Automated line-based sequential sampling and modeling algorithm for EMC near-field scanning
Part of IEEE transactions on electromagnetic compatibility (Print), p. 704-709, 2017
Conference papers
Adaptive Robust Learning using Latent Bernoulli Variables
Part of Proceedings of the 41st International Conference on Machine Learning, p. 23105-23122, 2024
Efficient Resource Scheduling for Distributed Infrastructures using Negotiation Capabilities
Part of 2023 IEEE 16th International Conference on Cloud Computing (CLOUD), p. 486-492, 2023
To test, or not to test: A proactive approach for deciding complete performance test initiation
Part of BIG-DATA 2022, p. 4758-4767, 2022
Scalable federated machine learning with FEDn
Part of 2022 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing (CCGrid 2022), p. 555-564, 2022
Robust and integrative Bayesian neural networks for likelihood-free parameter inference
Part of 2022 International Joint Conference on Neural Networks (IJCNN), p. 1-10, 2022
Proactive Autoscaling for Edge Computing Systems with Kubernetes
2021
Towards Smart e-Infrastructures, A Community Driven Approach Based on Real Datasets
Part of Proceedings of the 2020 IEEE Green Technologies Conference (GreenTech), p. 109-114, 2020
Learning surrogate models of document image quality metrics for automated document image processing
Part of Proc. 13th IAPR International Workshop on Document Analysis Systems, p. 67-72, 2018
Hyperparameter optimization for approximate Bayesian computation
Part of Proc. 50th Winter Simulation Conference, p. 1718-1729, 2018
Part of Proc. 32nd European Simulation and Modelling Conference, p. 22-27, 2018
Surrogate assisted model reduction for stochastic biochemical reaction networks
Part of Proc. 49th Winter Simulation Conference, p. 1773-1783, 2017
Automatic document image binarization using Bayesian optimization
Part of Proc. 4th International Workshop on Historical Document Imaging and Processing, p. 89-94, 2017