Aditya Anantharaman

I am a final year Undergraduate student currently pursuing my Bachelor's degree in Information Technology at National Institute of Technology Karnataka, Surathkal, India.

I am currently working as a Research Intern at the Visual Learning and Intelligence (VIGIL) Lab at Indian Institute of Technology, Hyderabad, India under Dr. Vineeth Balasubramanian.

In the summer of 2018, I interned at Microsoft (R&D), Hyderabad, India in the Azure Networking Team.

Email  /  Resume  /  Github  /  LinkedIn


My interests include Machine Learning, Deep Learning, Natural Language Processing, Computer Vision and Data Mining.

An Approach for Multi-modal Medical Image Retrieval using Latent Dirichlet Allocation
Mandikal Vikram, Aditya Anantharaman, Suhas B S, Sowmya Kamath
The ACM India Joint International Conference on Data Science & Management of Data (CoDS-COMAD), Kolkata 2019 (Oral Presentation)
A short version is accepted at the AI for Social Good Workshop, NIPS, Montreal, 2018
[Paper] [Poster] [Code]

Latent Dirichlet Allocation (LDA) based technique for encoding the visual features of the medical images along with novel early fusion and late fusion techniques to combine the textual and visual features.

Microsoft (R&D), Hyderabad, India
May - July 2018

Worked in the Microsoft Azure Networking team and developed a Test Cluster management, monitoring and usage plug and play service. Built a UI dashboard for interacting and reporting alongside the service.

Selected Projects

Paraphrase Detection using Deep Learning
Jan - Mar 2018
[Report] [Code]

Applied paraphrase detection to the medical domain of clinical notes. Developed a Bidirectional RNN based model with multi perspective matching and Attention.

Parallel k-means Clustering
Sep - Nov 2017

Used k-means clustering for Image Colour Quantization and Image Compression. k-means clustering implemented in parallel on 3 platforms - OpenMP, CUDA and MPI with performance comparison. Obtained a speed of order 10^3 in CUDA due to data parallelism and a compression factor of 2.2.


Image Credits: Link

Android Malware Detection
Jan - Mar 2018

Classification of android apps done based on pseudo-dynamic analysis of system API Call sequences. Developed a Deep Autoencoder model for feature compression along with a CNN and RNN model.


LIBO - Android App
Oct 2016
[Certificate] [Code]

Smart Library management app which integrates Microsoft Azure database and Microsoft cognitive services (OCR) and also uses basic recommender systems with the help of the apriori algorithm. Won 2nd position in online round of Microsoft hackathon.

Website Template