Study the effects of chaos in a custom LSTM architecture
We will use chaotic maps to initialise our parameters and study the change in performance of our custom LSTM on stock price prediction.
The project is for 1 semester. This is a research project, and can continue as long as you're willing to work.
Domain - Deep Learning, Chaos theory
Prerequisite - Deep learning, basic machine learning concepts
Understanding of Chaos theory is not required but you will have to learn basic concepts while working.
Skills - Python
Basic knowledge about PyTorch
Goal - Improve the performance of custom LSTM using chaotic initializations.
Current Status - The custom LSTM architecture is completed and has been tested for blood glucose prediction.
Expectations - Create a stock price dataset and modify the current LSTM to work on this new data. Also implement chaotic initialization in the LSTM architeccture.
- Abhijeet Swain
- Vaibhav Ganatra
Dr. Snehanshu Saha is our faculty supervisor. You can find more about him here