Research in the same computational neuroscience lab as my Neurogati work.

Developing brain-inspired intelligent systems by integrating AI and computational neuroscience.

Creating novel solutions in spatial reasoning, computer vision, and scalable health-tech applications.

Developed a system that uses Graph Database, Graph Neural Networks and Large Language Models(LLMs) to navigate a grid world, answer user queries, and provide relevant information about the environment.

Processed the dataset to store it in a Neo4j graph database and for other downstream tasks.

Used the LLM(Llama3) to question the graph database and generate Cypher queries for the questions asked by the user. The prompts were dynamically tuned using Langchain to improve query generation.

Implemented Q-learning method to explore the grid world. Used the explored data to query the graph neural network using the LLM(Llama3).

Presented this work at the 5th Annual Research Showcase, IIT Madras.

The project involved matching retail pet and grocery products to market conditions for effective pricing.

The project managed a substantial dataset of 5TB, featuring over 100 million products with comprehensive attributes such as titles, images, descriptions, sizes, flavours, model numbers, and UPCs.

Exploratory analysis was conducted on text and string-based data utilising Python libraries and SQL queries via AWS Athena.

A Transformer-based model architecture with Approximate KNN was developed, which was evaluated for its performance, achieving benchmark F1 scores of 96% against the WDC product matching benchmark and 91% against an internal evaluation dataset.

Core coursework in Data Structures, Algorithms, and Machine Learning.

CGPA: 7.60/10