Projects
Projects
A PyTorch reinforcement learning library centered around reproducible and generalizable algorithm implementations.
A PyTorch library to easily facilitate knowledge distillation for custom deep learning models
Neural Correlates for Reinforcement Learning
A review of the connections between neuroscience and reinforcement learning.
DeepTime
An exploratory and experimental research into the applications of modern deep learning breakthroughs in traditional time-series analysis approaches.
ADReSS
Alzheimer's Dementia Recognition from Spontaneous Speech. The aim is unbiased early detection of cognitive decline from multi-modal data.
SNNs to Validate Experimental Results
Building computational spiking neural network models to model neural functioning and thereby validate experimental results.
A Python Library for Robustness Monitoring and Adversarial Debugging of NLP models.
IKD-DAFL
DAFL(Data free learning) is an unsupervised Knowledge Distillation technique. We are trying to apply IKD on this technique for smaller datasets as of now like MNIST/CIFAR.
A python library consisting of pipelines for visual analysis of different sports using Computer Vision and Deep Learning.
Sponsored Projects
FlashFill Implementation in Julia
Participant(s): Atharv Sonwane
Program: Google Summer of Code, 2022
Organization: Julia Language
Funding Agency: Google
Grant Amount: $1500
Classification of body keypoint trajectories of gesture co-occurring with time expressions
Participant: Shrey Pandit
Program: Google Summer of Code, 2022
Organization: Red Hen Lab
Funding Agency: Google
Grant Amount: $1500
Add Gen converter to ArviZ.jl (Julia)
Participant(s): Harini S I
Program: Google Summer of Code, 2022
Organization: NumFOCUS
Funding Agency: Google
Grant Amount: $1500
Creating Benchmark Datasets for Object Recognition with Event-based Cameras
Participant: Neelay Shah
Program: Google Summer of Code, 2022
Organization: INCF
Funding Agency: Google
Grant Amount: $1500
Participant(s): Avishree Khare & Het Shah
Program: European Summer of Weather Code, 2021
Funding Agency: European Center for Medium Range Weather Forecasts (ECMWF)
Grant Amount: $6000
Participant: Vedant Shah
Program: Google Summer of Code, 2021
Organization: GFOSS
Funding Agency: Google
Grant Amount: $1500
Normalizing Flows for Fast Detector Simulation
Participant: Aditya Ahuja
Program: Google Summer of Code, 2021
Organization: ML4SCI
Funding Agency: Google
Grant Amount: $1500
A Python toolbox for computing high-order information in neuroimaging
Participant: Pranav Mahajan
Program: Google Summer of Code, 2021
Organization: INCF
Funding Agency: Google
Grant Amount: $1500
Participant: Sharad Chitlangia
Program: Microsoft RLOS Fest
Grant Amount: 10000$
Funding Agency: Microsoft Research
Short description of proposal: Addition of new serialization protocols for input examples, model files in VowpalWabbit for extremely fast and scalable Machine Learning.
Applying AI capabilities to address Operations challenges in ECMWF Products Team
Participant: Aditya Ahuja
Program: European Summer of Weather Code, 2020
Grant Amount: 6000$
Funding Agency: ECMWF
Past Projects
Stock market Modelling using Reinforcement Learning
This project in collaboration with ISI Kolkata aims to apply deep Reinforcement learning to financial trading markets in order to develop a Markov decision process which will suitably capture any general financial market.
Implementation of Neural Voice Cloning with Few Samples paper by Baidu Research
Drone performing imitation learning on IDSIA dataset. Project funded by EEE department and Academic Graduate Studies & Research Division
Word2Brain2Image: Visual Reconstruction from Spoken Word Representations
Collected EEG data of subjects listening to spoken object words. We attempted to use deep generative models to generate images of objects using only this EEG data, in order to study internal representations in visual association areas (BA 18,19) of the brain.
Research Project in unofficial collaboration with TCS Research. Applying State of the art models for pneumonia detection on RSNA pneumonia detection dataset. Tested InceptionNet-v3, DenseNet121 and explored Mask RCNN applicability for the dataset. Got 83.8% and 77.9% classification accuracy respectively.
Emotion Recognition From EEG Signals
A project with the aim to use deep convolutional networks on EEG signals in order to predict valence and arousal values from them.
Dynamic Gesture Recognition for controlling portable devices
Using detected dynamic gestures such as swiping left/right, closing fist, etc. to control portable devices ( multitasking / controlling video playback, etc. )