I focus on developing a strong theory group on Machine learning and Deep Learning, specifically addressing the complex issue of optimization in Learning and attempting to unfold the ‘black-box’ deep learning techniques. I develop methods in Computational Learning Theory (COLT) and Mathematics of Data Science (MDS) Techniques and focus on building Pointwise smooth approximations of gradient, discovering activation functions from data, smoothness and convexity studies of loss functions, methods in interpretable deep learning, novel loss functions in back-propagation, Chaos-causality in Deep Neural Networks and pruning/compression in Deep Networks. My Goals include Efficient, reliable and robust Inferences (One Landscape) via tools such as Measure Theory, Non-Linear Optimization, Functional Analysis, Econometrics and Dynamical Systems. I apply the methods to solve problems in Biology, Healthcare, AstroInformatics (AIM), Transportation, and other Social good applications (AML).Recent Notable Publications (2022-23):1. N.Arya, A. Mathur, Sriparna Saha, S.Saha; Improving the Robustness and Stability of a Machine Learning Model for Breast Cancer Prognosis through the use of Multi-Modal Classifiers; ScientificReports (Nature) [Q1, I.F: 5]2. N.Arya, A. Mathur, S.Saha, Sriparna Saha; Proposal of SVM Utility Kernel for Breast Cancer Survival Estimation; IEEE/ACM Transactions on Computational Biology and Bioinformatics [Q1, I.F: 3.74]3. J.Sarkar. S.Saha, S.Sarkar; Efficient Anomaly Identification in Temporal and Non-Temporal Industrial Data using Tree Based Approaches; Applied Intelligence [Q1, I.F: 5.4]4. Aishwarya. M, V.Raychoudhury, S. Saha, S.Kar, Anusha. K, CARE-Share: A Cooperative and Adaptive Ride Strategy for Distributed Taxi Ride Sharing, IEEE Transactions on Intelligent Transportation Systems [Q1, I.F: 9.98]5. A. Tambewkar, A. Maiya, Soma.S. Dhavala and S.Saha; Estimation and Applications of Quantiles in Deep Binary Classification; IEEE Transactions on Artificial Intelligence6. Tejas Prashanth, Snehanshu Saha, Sumedh Basarkod, Suraj Aralihalli, Soma S Dhavala, Sriparna Saha, and Raviprasad Aduri; LipGene: Lipschitz continuity guided adaptive learning rates for fast convergence on Microarray Expression Data Sets’ [Q1, I.F: 3.74]7. Rohan Mohapatra, Snehanshu Saha, Carlos A. Coello Coello, Anwesh Bhattacharya, Soma S. Dhavala and Sriparna Saha; AdaSwarm: Augmenting gradient-based optimizers in Deep Learning with Swarm Intelligence, the IEEE Transactions on Emerging Topics in Computational Intelligence [Q1, I.F: 4.9]