Mrinal Das

About

Prof. Mrinal Das is an Associate Professor in the Department of Data Science at IIT Palakkad. His expertise is in the areas of machine learning, deep learning, computer vision, and natural language processing. Currently, he has been more active in the areas of generative AI, responsible AI, privacy-aware learning, and meta learning. He obtained a PhD degree in Machine Learning from the Indian Institute of Science (IISc), Bangalore, in 2016. He was a postdoctoral fellow at Aalto University, Finland, and UMass Amherst, USA, before joining as an Assistant Professor at IIT Palakkad in 2017. He has received multiple project grants and has published in top-notch venues in ML, such as ICML, AAAI, ICDM, CIKM, WSDM, as well as reputed journals such as Scientific Reports. He has developed and taught several courses in the area of Data Science for the last eight years. He is also actively associated with the Government of Kerala for spreading awareness and skills in data science among students, teachers, as well as professionals.

Employment

• Indian Institute of Technology Palakkad Associate Professor
  2025 - Present
• Indian Institute of Technology Palakkad Assistant Professor
  2021 - 2025
• Indian Institute of Technology Palakkad Assistant Professor
  2017 - 2021
• University of Massachusetts Amherst Postdoc
  2016 - 2017
• Aalto University Postdoc
  2014 - 2016
• Indian Institute of Science PhD
  2007 - 2014

Education

Education history is unavailable.

Projects & Funding

Projects & funding information is unavailable.

Publications (31)

• Map wisely for efficient transfer learning across heterogeneous data sources
  Neurocomputing 2026 DOI: 10.1016/j.neucom.2025.131762
  +Save
• Modeling task uncertainty for neural processes to meta-learn with fewer tasks
  Neurocomputing 2026 DOI: 10.1016/j.neucom.2026.133417
  +Save
• A supervised learning approach for recommending medical specialists in the healthcare sector for the Afaan Oromo context
  Discover Computing 2025 DOI: 10.1007/s10791-025-09556-8
  +Save
• Contrastive Loss Coupled with Occlusion Aware Training Aids in Face Recognition from Low Quality Group Photos
  3rd International Conference on Microwave Optical and Communication Engineering Icmoce 2025 2025 DOI: 10.1109/ICMOCE64100.2025.11076788
  +Save
• Focus On What Matters: Guiding Vision Transformers Towards Justification
  Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD) 2025
  +Save
• Focus on What Matters: Guiding Vision Transformers Towards Justification
  Lecture Notes in Computer Science 2025 DOI: 10.1007/978-981-96-8180-8_15
  +Save
• MLP-SVM: a hybrid approach for improving the performance of the classification model for health-related documents from social media using multi-layer perceptron and support vector machine
  Discover Applied Sciences 2025 DOI: 10.1007/s42452-025-06851-3
  +Save
• Catch them Unattentive: An Orientation Aware Face Recognition Model
  Lecture Notes in Networks and Systems 2024 DOI: 10.1007/978-3-031-66336-9_7
  +Save
• Human Guided Multi-proportions Topic Model for Rare Event Detection Without Using Labels
  Lecture Notes in Networks and Systems 2024 DOI: 10.1007/978-3-031-66336-9_26
  +Save
• Human Guided Multi-Proportions Topic Model for Rare Event Detection without using Labels
  Intelligent Systems Conference (IntelliSys) 2024
  +Save