Yeshwanth Ravi Theja Bethi
Research Student - MPhil
Research Program: International Centre for Neuromorphic Systems(opens in a new window)
Reinforcement learning using spiking neural networks and event-based sensors
In recent years, deep learning has revolutionized the field of machine learning and for computer vision tasks in particular. The results produced by Artificial Neural Networks (ANNs) have even surpassed human capabilities in some tasks. Spiking Neural Networks (SNNs) are more biologically plausible than ANNs and exploring them also helps in understanding the brain and how it computes. SNNs are also more hardware friendly and energy efficient than ANNs. They are appealing especially for portable and edge technology for the same reason. However, the SNNs still lag behind the ANNs in terms of accuracy in computer vision tasks.
My research aims to bridge that gap by utilizing the spiking nature of Event-based sensors to build novel and better SNN architectures for computer vision tasks.
- B.Tech in Electrical Engineering from Indian Institute of Technology Bombay
|Location||Western Sydney University Werrington South campus|