Worked on a battery model calibration using reinforcement learning project. Proposed actor-critic RL algorithm with Lyapunov constraint regularization for robust calibration of model

Worked on continual learning for image classification in digital pathology. Developed a method which remember the past knowledge via distillation. This method works in replay-free task-incremental setting.

Worked on building trading strategies using alpha signals from many sources. Applied techniques for filtering useful trading signals and combining them to make profitable strategies.

Worked on various client facing projects. Handled projects with teams across different offices in the US and India. (1)Patient desease progression modeling using patient history (ICD9 codes) (2) Multi channel marketing optimization for pharma companies (3) Real-time analytics for the sales representatives to make better decisions