I am a final year undergraduate student pursuing a Double Major in Computer Science and Mathematics at BITS Pilani, Goa. I'm currently working on my senior thesis on Deep AutoML and Video Compression Research at Intel Labs and am also working on time-series anomaly detection for servers with ECMWF.

In the past, I've been extremely fortunate to have gotten the opportunity to work on funded research projects under the guidance of Prof. Ashwin Srinivasan and Prof. Tirtharaj Dash with TCS Research and the Anuradha and Prashanth Palakurthi Centre for Artificial Intelligence Research (APPCAIR) at BITS Goa .

My current research interests are focused towards (but aren’t limited to) Generative Modelling, Meta-Learning and Transfer Learning, particularly for Computer Vision. I also have dabbled a bit in Time-Series Forecasting and Anomaly Detection research and application.

Feel free to drop me an e-mail if you want to chat with me! :)
BITS Pilani
2016 - Present
TCS Research
2019 - 2020
Goldman Sachs
Intel Labs
2020 - Present

[ News  |  Education  |  Work Experience  |  Open Source  |  Teaching  |  Publications ]


[ Nov '20 ]

Here's a talk by me and my teammate, Aditya about our work at ECMWF. [Video]

[ Aug '20 ]

Our paper on the detection of COVID-19 from chest X-rays got accepted at the TIA Workshop at MICCAI 2020!

[ Aug '20 ]

Excited to be one of the 150 students selected for the Google Research India AI Summer School!

[ Jul '20 ]

I'll be working with Intel Labs as a Graduate Research Intern for this year!

[ May '20 ]

I'll be working as a ML research intern at ECMWF as part of their summer program - ESoWC.

[ May '20 ]

I'll be interning at Goldman Sachs as a Summer Analyst in Regulatory Metrics and Resillience (RMR) team.

[ Jan '20 ]

I'll be working on a sponsored semester projects with TCS Research on Medical Imaging and Meta-learning for Handwritten Text Recognition.

[ Jan '20 ]

I'll be the Lead TA for the Machine Learning Course at BITS Pilani, Goa. (2nd time)

[ Aug '19 ]

I'll be TAing the Machine Learning Course at BITS Pilani, Goa.

[ Aug '19 ]

I'll be working on a sponsored semester project with TCS Research on Meta-learning for Time-Series Forecasting

[ Jul '19 ]

I'll be attending the 4th Summer School on Machine Learning at IIIT-H!

[ May '19 ]

I'll be interning this summer with the Deep Meta-Learning group at TCS Research


BITS Pilani KK Birla Goa Campus
August 2016 - Present

B.E in Computer Science and M.Sc in Mathematics (Double Major)
CGPA: 9.15

Work Experience

Intel Labs
July 2020 - Present

Graduate Research Intern

Currently working on Deep AutoML and Video Compression research

European Centre for Medium-Range Weather Forecasts
May 2020 - Present

Research Intern | European Summer of Weather Code | Mentors: Dr. Peter Deuben, Matthew Manousakkis

ECMWF is an intergovernmental organisation that provides terabytes of meteorological data every day to multiple organizations and clients. Due to the scale, disruptions in the service can be very expensive.
Working on building a robust real-time time-series anomaly detection system using server log data to detect ECMWF server health and predict crashes,sudden disruptions and failures. as part of the European Summer of Weather Code 2020.

Goldman Sachs
May 2020 - June 2020

Summer Analyst | Engineering Division

Built data pipelines and visualizations to help teams understand changes in developer work patterns and productivity during the COVID-19 crisis to enable teams to support employees better. Worked with ELK ( Elasticsearch - Logstash - Kibana ) stack. Code currently being used in production

TCS Research and Innovation
May 2019 - July 2020

Research Intern (in collaboration with APPCAIR,BITS Goa)

Worked on multiple research projects over the period of a summer and two semesters. Advisors : Prof. Ashwin Srinivasan, Prof. Tirtharaj Dash, Dr Lovekesh Vig, Pankaj Malhotra

Medical Imaging for COVID detection

Worked on building a DL based tool to assist radiologists. Built a pipeline comprising of lung segmentation/isolation U-Net model, followed by classifier augmented with symptom embeddings produced by the CheXpert network. Used explainablity methods (GradCAM, DeepLIFT) to provide interpretable and relatively trustworthy decisions.

Meta Learning for Handwritten Text Recognition

Worked on using applying meta-learning based algorithms (REPTILE and MANN) to seq-2-seq based C-RNN models to effectively recognize handwritten text from documents in low-resource languages.

Meta Learning for Time-Series Forecasting

Worked on an building a robust time-series forecasting model that can learn to forecast well from cold starts. Experimented with transfer learning and optimization-based meta-learning approaches such as REPTILE and CAVIA on various time-series forecasting models

Designed a fast and online solution for Drone Control using an EEG signal based Brain-computer Interface that also deals with the non-stationarity and inter-user variation of the data using Extreme Learning Machines and Deep Belief Networks.

Open Source

BlackSwan - Realtime Streaming Anomaly Detection on Time Series [Repository]

Developed a package for realtime timeseries Anomaly Detection. Implemented and integrated several state of the art ML and DL Anomaly Detection and Forecasting algorithms with a realtime graphical interface.
This work was funded by ECMWF's open source program - the European Summer of Weather Code.


[ Demo | Full Size ]

[ Demo | Full Size ]

Check out the Independent Demo Page for more information!

[ Go to Independent Demo Page ]


[Spring '20]

BITS F464: Machine Learning - Head Teaching Assistant

[Fall '19]

BITS F464: Machine Learning - Teaching Assistant

[Spring '19]

BITS Work Integrated Learning Programmes (WILP) - MATH ZC233: Calculus - Teaching Assistant

[Fall '18]

BITS Work Integrated Learning Programmes (WILP) - MATH ZC233: Calculus - Teaching Assistant

[Spring '18]

CS F111: Computer Programming - Teaching Assistant


CovidDiagnosis: Deep Diagnosis of COVID-19 Patients using Chest X-rays
The Second International Workshop on Thoracic Image Analysis, MICCAI 2020

Design and source code inspired from Sebastin Santy's, Jon Barron's and Aditya Ahuja's great Academic websites. :)