We work in theory as well as applications related machine learning and data science. Our expertise ranges from optimization, control to Bayesian models in theory, whereas Bioinformatics, education to zoonotic pandemics.
Centre for Research and Education Data Science is lauched in IIT Palakkad. Our group is a key contributor in CREDS.
Dr. Mrinal Das has received SERB start-up research grant to work on the project of "Bayesian Deep Models for Efficient Privacy-Aware Learning in the Era of Big Data and Personalization".
BTech project of Anish MM with joined supervision of Dr Deepak from Queens University and Dr. Sahely Bhadra from IIT Palakkad has been accepted to be presented in Time series workshop of ICML 2019
Dr. Sahely Bhadra visited Aalto University in summer 2019 on Indo-Finish Mobility Grand from DST and Academy of Finland.
Large-Scale Sparse Kernel Canonical Correlation Analysis.[Pdf] Viivi Uurtio, Sahely Bhadra, Juho Rousu. Proceedings of the 36th International Conference on Machine Learning(ICML) 6383--6391,2019.
Sparse Non-Linear CCA through Hilbert-Schmidt Independence Criterion.[Pdf] Viivi Uurtio, Sahely Bhadra, Juho Rousu. IEEE International Conference on Data Mining(ICDM),2018.
Weight-Agnostic Hierarchical Stick-Breaking Process.[Pdf] Mrinal Kanti Das, Chiranjib Bhattacharyya. IEEE International Conference on Big Knowledge, 2018.
SOPER: Discovering the influence of fashion and the many faces of User from Session logs using Stick Breaking Process.[Pdf] Lucky Dhakad, Mrinal Kanti Das, Chiranjib Bhattacharyya, Samik Datta, Mihir Kale, Vivek Mehta. International Conference on Information and Knowledge Management (CIKM), 2017.[Link]
Efficient differentially private learning improves drug sensitivity prediction. [Pdf]. Antti Honkela*, Mrinal Das*, Arttu Nieminen, Onur Dikmen, Samuel Kaski.Biology Direct, 2018 (* equal contribution)
We have developed two web based tools: LeSi and xDet. LeSi is a Machine Learning based Learner Simulator for studying spread of Covid19 in India and various states. LeSi is based on 10-compartment pandemic model adapted from SEIR. LeSi allows users to learn location specific parameters from real cases. LeSi also allows users to run a pandemic simulator in forecasting mode. xDet is a Machine Learning based tool to classify X-ray images among various respiratory diseases.