See a map of all the places I've given a talk!
Talk, Electrical Engineering, IIT Bombay, Mumbai, India
This was a hands-on session on machine learning for officers of Indian Post & Telecom Accounts Finance Service (IP&TFAS) of 2018 batch.
Talk, Satish Dhawan Auditorium, IISc Banglore, Bengaluru, India
This was a presentation of our entry to Intel Python Hacfury2. We won second prize worth 1 lakh rupees. 
Tutorial, Department of Electrical Engineering, IIT Bombay, Mumbai, India
The agenda of the talk was to demonstrate basic machine learning and dimensionality reduction tecnique. The resources for the tutorial are here.
Talk, Department of Electrical Engineering, IIT Bombay, Mumbai, India
This talk presents an overview of the domain of deep learning. It was aimed for first year graduate and undergraduate students of Electrical Engineering department of IIT Bombay. The resources for the talk are here.
Tutorial, Department of Electrical Engineering, IIT Bombay, Mumbai, India
This is a joint tutorial by Prof. Amit Sethi, Abhijeet Patil and me. The agenda of the talk was to demonstrate basic machine learning on sensor data. We presented an use-case of forecasting power-consumption using the weather features like temperature, pressure, wind etc. The resources for the tutorial are here.
Conference proceedings talk, 26th International Conference on Systems, Signals and Image Processing, IWSSIP 2019, Osijek, Croatia
Normalizing unwanted color variations due to differences in staining processes and scanner responses has been shown to aid machine learning in computational pathology. Of the several popular techniques for color normalization, structure preserving color normalization (SPCN) is well-motivated, convincingly tested, and published with its code base. However, SPCN makes occasional errors in color basis estimation leading to artifacts such as swapping the color basis vectors between stains or giving a colored tinge to the background with no tissue. We made several algorithmic improvements to remove these artifacts. Additionally, the original SPCN code is not readily usable on gigapixel whole slide images (WSIs) due to long run times, use of proprietary software platform and libraries, and its inability to automatically handle WSIs. We completely rewrote the software such that it can automatically handle images of any size in popular WSI formats. Our software utilizes GPU-acceleration and open-source libraries that are becoming ubiquitous with the advent of deep learning. We also made several other small improvements and achieved a multifold overall speedup on gigapixel images, processing $10^9$ pixels in 3 minutes. Our algorithm and software is usable right out-of-the-box by the computational pathology community.
Tutorial, Department of Electrical Engineering, IIT Bombay, Mumbai, India
This is a joint talk by Prof. Amit Sethi and me. The agenda of the talk was to demonstrate some areas in the domain of electrical engineering where deep learning can be used as a computational tool. We presented some interesting use-cases like computation of fields in a complex environment, load prediction in grids, identification of modulations in channels, and some computer vision tasks.
Poster, Tata Centre for Technology and Design Symposium 2019, Mumbai, India
Demonstrated an in-house, built android app for oral cancer screening. The app takes in the clinical images of the interior of the mouth, identifies a potential lesion, and predicts the class of pre-cancerous lesions.
Poster, NVIDIA’s workshop on The Convergence of HPC with AI, Bangalore, India
Discussed many applications of deep learning in the healthcare and presented a method to identify HER2 mutation in breast cancer histopathology whole-slide images.