Akshay Raj Gollahalli

Akshay Raj Gollahalli is currently doing his PhD under Prof. Nikola Kasabov and Dr. Michael J. Watts. His topic of study is "A platform independent Spiking Neural Network framework with Markup Language".

Akshay is currently working on the development of new markup language for Spiking Neural Network (SNN) called Spikes Markup Language (SML) that could be used to deploy on multiple platforms. He is also working on the development of a new framework for SNN called Spikes with support for Neuromorphic systems, Graphical Processing Unit (GPU) and other embedded systems.

He will be using the Spikes framework with SML on three case studies:

  1. Behavourial cloning
  2. Cognitive games
  3. Financial trade prediction

Links to relevant web pages:

Qualifications:

  • Bachelor of Technology in Computer Science and Engineering (B.Tech CSE) from Jawaharlal Nehru Technological University, Hyderabad, India (2012)
  • Masters of Computer and Information Sciences (MCIS) (First Class Honours) from Auckland University of Technology, Auckland, New Zealand (2016)

Memberships:

  • IEEE Student Member

Prizes or Scholarships:

  • Knowledge Engineering and Discovery Research Institute Fee Scholarship Holder, AUT University in 2017
  • Dean’s Award for Excellence in Postgraduate Study, AUT University in 2016
  • Knowledge Engineering and Discovery Research Institute Tuition Scholarship Holder, AUT University in 2016
  • Lead blood donor, Lions Club, India in 2013

Teaching area:

  • INFS600 – Data and Process Modelling 1/2018
  • COMP400 – Foundation Programming 1/2018

Research area:

  • Computational Neuroscience
  • Machine learning
  • Computer Vision
  • Self-Driving Cars
  • Brain-Computer Interfaces
  • Neuromorphic systems
  • Cloud Computing
  • Artificial Neural Networks
  • Spiking Neural Networks

Publications:

Journal

  • Khansama, R., Ravi, V., Sengupta, N., Gollahalli, A. R., & Kasabov, N. (2017). Stock market movement prediction using evolving spiking neural networks. IEEE Transactions on Neural Networks and Learning Systems. (Submitted)