logo logo

About Me

I am part of the Advanced Processor Technology (APT) group here at The University of Manchester and I am supervised by Mr. Graham Riley and Dr. Mikel Lujan . My research is part funded by ARM and IS-ENES2 Project.
My research topic is "Efficient execution of Convolutional Neural Networks on low power heterogenous systems". If I had to sum up my research in three words, it would be Convolutional Neural Networks ( a.k.a "ConvNets"), Heterogenous Computing and Energy-Efficiency.

My research

Teaching Assistant

Apart from my research, I work part-time as a Teaching Assistant for the following modules:

Conferences and Summer Schools

Student Blogger

I also actively post monthly blogs about my experiences as a postgraduate research student.

Student Volunteer

I engage in fund-raiser activities with Manchester RAG and open day activities as CS student volunteer. I was also a Business Ambassador for the TeenTech event held in Manchester, April 2016.
RAG

Other Roles

Timeline

    Undergraduate-ECE May 2013
    B.E in E&C- 9.06%
    Manipal Institute of Technology, Karnataka
    Application engineer August 2014
    Tata Consultancy Services Ltd, Goa
    Postgraduate-Computer Science September 2015
    MSc.In Advanced Computer Science- Artificial Intelligence Distinction
    The University of Manchester
    PhD- Computer Sciencce October 2015
    PhD in Computer Science
    The University of Manchester
    ARM Research internship August 2017-October 2017
    ARM Research

Publications

To be presented at IISWC 2017

Fine-grained energy profiling of deep convolutional neural networks on the Jetson TX1

IEEE Xplore (2014)

Echo Canceller Using Error Back Propagation Algorithm

International Journal of Computer Applications (2014)

Performance Evaluation of Error Back Propagation Algorithm for Non-Linear Classification and Function Approximation in VHDL Platform

Master's Dissertation

Master's Dissertation-School of Computer Science library - 2016

Exploring the transfer learning aspect of deep neural networks in facial information processing

Projects

CO2 much - 2015

It visualises an estimate of the CO2 car emissions per manufacturer and per year.

CO2 much

Winners of CDL SOFTWARE CHALLENGE- GreatUniHack, December 2015

Interests

  • Ballroom and Latin Dance (Manchester University Ballroom and Latin Dance Society)
  • RAG
  • Hip hop and contemporary dance
  • Learning new languages- Portuguese (beginner), Arabic (basic), Greek (just started)!
  • Badminton
  • Swimming

Get In Touch