I am currently leading the Federated Learning team at OpenMined where we are building the first open source library for privacy preserving machine learning. Prior to this, I was a research scholar at UC Berkeley working on neural program synthesis.
I finished my undergraduate studies from IIT Kanpur in Computer Science and Engineering. After graduation, I went for a year long stint at MPI for Brain Research as a visiting research scholar exploring the intricacies of human brain.
My research interest lie in Machine Learning with a predilection for program synthesis, computer vision, and security.
Checkout my Resume. The details of the ongoing as well as past projects can also be found below.
BTech in Computer Science and Engineering, 2019
Indian Institute of Technology, Kanpur
Advisor : Dawn Song
Objective : Neural symbolic hybrids for few shot recognition
Using program induction to sample programs for few shot image classification.
Training procedure involves Supervised pre-training with teacher-forcing followed by reinforcement learning using Hindsight Experience Replay.
We use memory augmented networks with attention to allow multiple chains of execution.
Objective : Meta learning in SQL query synthesis
Divided the Spider dataset into 13 meta categories.
We use transformers to generate embeddings for natural language question tokens.
A meta-training phase for decoder to learn predicting the structure of SQL query
A domain specific training phase for token prediction using a separate multi head attention module.
Advisor : Prof. Moritz Helmstaedter
Objective : Myelin segmentation in 3D mSEM and connectomic analysis
We used 3D Unet trained on multi Scanning Electron Microscope raw data to generate 3D segmentation masks
Dynamically oversampling (with linearly decaying probability) myelinated voxel cubes to provide non-zero gradients countering highly skewed data (0.01% positively labeled voxels)
Reached over 90% precision-recall. Using the detection to analyze thalamocortical neurons with myelinated axons at the beginning of innervation.
Advisor : Prof. Tat Seng Chua
Objective: Monocular 3D object instance recognition and Pose Estimation
Proposed (alongside a post graduate student) a novel end-to-end architecture consisting of two modules for robust pose prediction and 3D instance recognition via extracting Marr’s 2.5 D sketches from images.
The learned embedding explicitly disentangles a shape vector and a pose vector, which alleviates both pose bias for 3D shape retrieval and categorical bias for pose estimation
One sub module learns to reconstruct 3D model, from the 2.5D sketches, in its canonical viewpoint via multi-task learning DNNs. Another NN sub module uses Faster R-CNN style anchor boxes to predict the 6 DoF poses in continuous domain.
The method achieves state of the art 10.3 median error for pose estimation and 0.592 top-1-accuracy for category agnostic 3D object retrieval on the Pascal3D+dataset.
Objective: Industrial grade deployment of ML backend and android application for NYO
Lead a team of 16 people at NYO.
ML systems:
Android app: REST APIs, SSE notifications, app-caching, Continuous integration with Jenkins, data and property binding, Reactive Java for observables