1. Home
Name

Project - Conversation Disentanglement using LLM

to use LLM and Q learning for build a model for conversation disentanglement
Available Apply By30/12/23

Project - Exploration of Geometric QML/ Group Invariant QML/ symmetries for optimization

Classically geometric invariances have been used in machine learning. Some recent works have proposed the same for quantum ML :- https://arxiv.org/pdf/2205.02261.pdf https://arxiv.org/pdf/2210.07980.pdf We will explore some of these and potential implementation in qiskit.
Available Apply By31/12/23

Project - Quantum Machine Learning for spatial tissue classification

Implement algorithms for QML in Qiskit + Pytorch including:- 1. Graph Neural Networks with VQC 2. Quantum Ansatz Design using RL
In progress

Project - PBE - for Logical, Syntactic, Semantic transformation - RL

To solve three task Logical, Syntactic, Semantic transformation using one framework
In progress

Project - Using Medical Data Analysis to Inform Early Prediction and Prevention of Chronic and Pandemic Diseases

The goal of this project is to analyze large volumes of medical data to identify patterns and risk factors that can aid in the early prediction and prevention of chronic and pandemic diseases within a specific region. By leveraging advanced analytical techniques, such as machine learning and data mining, the project aims to uncover valuable insights that can inform the development of targeted interventions aimed at reducing the burden of these diseases. Through this analysis, the project aims to identify common risk factors, symptoms, and disease progression patterns, as well as explore the impact of environmental factors on disease prevalence and incidence. The insights gained from this analysis can then be used to develop targeted interventions, such as public health campaigns, new diagnostic tools, and policies aimed at promoting healthy behaviors and lifestyles. Overall, the project seeks to contribute to efforts to improve population health and mitigate the impact of chronic and pandemic diseases by gaining a deeper understanding of the underlying factors that contribute to disease and developing effective prevention and treatment strategies.
In progress

Project - Exploring regions where model works and does not work and then using this information to sample relevant feedback data.

The main idea of this work is to explore regions where a given model does not work. Using this information, can we extract relevant feedback data that can be used to improve model's performance?
In progress

Project - LLMs for Legal Text Analytics

1. To train a LLM for use in Legal Text Analytics tasks. 2. To explore extracting a knowledge graph from an LLM.
In progress

Project - Challenges in Utilizing Spot Instances with Distributed Cluster Environments

This project aims to discuss the difficulties and risks associated with using Spot Instances in a distributed cluster environment setup. Spot Instances offer cost savings, but are subject to interruptions and unpredictable pricing, making it challenging to use them in a distributed cluster environment where data reliability and availability are critical. This project highlights the need for careful planning and implementation to successfully utilize Spot Instances in distributed cluster environments.
In progress

Project - Coarse grained Protein folding modelling and simulation in Quantum Computers

1. Understanding of the QC algorithms on protein folding that are available. Will require literature survey. 2. Implementation of some of the models that look promising. Develop experience and draw inference from collected data/results. 3. Propose new models or suggest changes to the existing models.
In progress

Project - Quantum-Estimation of excited energy states in a electronic structure problem

1. Study the theoretical aspects of existing methods of estimating excited states. 2. Implement them on a quantum simulator/hardware. 3. Compare the methods in terms of ease of applicability and accuracy. 4. Propose changes to the algorithms to improve on the above factors. 5. Publish if possible.
In progress