Research

Engineering Sciences

Title :

Investigation of Orthogonal Regularized Deep Neural Networks for Classification Tasks

Area of research :

Engineering Sciences

Principal Investigator :

Dr. Jeevanand S, Indian Institute Of Technology (IIT) Roorkee, Uttarakhand

Timeline Start Year :

2023

Timeline End Year :

2026

Contact info :

Details

Executive Summary :

OrthDNNs are theoretically motivated by generalization analysis of modern DNNs, with the aim to find solution to properties of network weights, that guarantee better generalization. This work is an effort to develop the theoretical framework and show OrthDNN’s applicability in mainly classification tasks such as early fault diagnosis in electric drives, which is an important issue, especially in sectors such as EV, aerospace and marine. So, this research on orthogonal deep networks, based on deep neural networks, is a fast developing research topic, and a promising solution. Most importantly, this idea does not modify the existing structure / or add anything which would cause additional computational burden, which is of immense value in such applications.

Total Budget (INR):

6,60,000

Organizations involved