MACHINE LEARNING RESEARCHER & COMPUTER
I am a graduate student working in the field of Machine Learning and Reinforcement Learning at UC Berkeley, where I am advised by Dr. Ram Akella. I spent two years at Facebook and at MIT Media Labs working with Dr. Ramesh Raskar on problems in computer vision and deep learning.
My research interests are in Reinforcement Learning and Statistics. I am most excited about Decision Making under Uncertainty or problems that involve partial observability.
Most of my current work is around Bayesian Inference, Hidden Markov Models, Probabilistic Graphical Models, Variational Inference, Particle Filters, POMDPs, Model-based and Model-free learning, Inverse Reinforcement Learning, etc.
Relevant Courses I have taken at UC Berkeley: EECS227A-Optimization Models, CS281A/STAT241A-Statistical Learning Theory, CS294-Machine Learning for Systems, CS294-Deep Reinforcement Learning, STAT248-Time Series Analysis, INFO271B-Quantitative Research
Other Relevant MOOCs: Stanford CS231n Convolutional Neural Network for Visual Recognition, Stanford CS224N NLP with Deep Learning, Stanford CS288 Probabilistic Graphical Models, Berkeley CS287 Advanced Robotics, MIT18.065 Signal Processing for Machine Learning, MIT6.262 Discrete Stochastic Processes
Theory and practice
Technical Interest and Expertise
++C / C
MATLAB / R
MongoDB / NoSQL
AWS/ GCP/ Kubernetes
Scikit Learn / Numpy / Pandas
KEYNOTES & TALKS
My Ongoing Research. See More >
2018 July - Present
Master's Degree, Focus: Machine Learning
Graduate Student Researcher
Working on various research projects in the domain of Reinforcement Learning and Statistics.
2019 June - Present
Research Scientist Intern
Working on two research projects - one in the domain of Inverse Reinforcement Learning and another in Secure Federated Learning.
MIT Media Labs
Trained several pose estimation models like OpenPose and DensePose-RCNN in PyTorch framework to detect yoga poses real-time and deployed it on mobile platforms. Advised by Dr. Ramesh Raskar from MIT Media Lab.
Software Engineer (Machine Learning)
Developed an automatic generative algorithm to create street addresses from satellite images by learning and labeling roads and regions. Trained various models like SegNet, U-Net, VGG, and ResNet for segmentation and detection.
2015 - 2016
DRDO, Ministry of Defence, Govt. of India
Developed unsupervised learning algorithms to identify important features in order to detect workload in soldiers’ brains using 14, 64, 256 channel EEG data.
2014 - 2015
Indian Academy of Sciences
Used a core-periphery structure model to detect the spread of virality in an online social network. Developed a Preferential Attachment Model to demonstrate real-time Facebook Graphs and tested those models on a citation and the collaboration network.
University of Mumbai
Bachelor's Degree, Computer Science
Courses Taken: Linear Algebra, Probability and Statistics, Multivariate Calculus, Algorithms and Data Structures, Operations Research, Artificial Intelligence, ERP and Supply Chain Management, Big Data Analytics
I'm graduating in May 2020 and open to full-time opportunities in research. Get in touch if my profile looks like a match!