Zawar Qureshi

London Area, United Kingdom Contact Info
536 followers 500+ connections

Join to view profile

About

Software engineer specialised in computer vision, machine learning & optimisation…

Activity

Join now to see all activity

Experience & Education

  • Niantic, Inc.

View Zawar’s full experience

See their title, tenure and more.

or

By clicking Continue to join or sign in, you agree to LinkedIn’s User Agreement, Privacy Policy, and Cookie Policy.

Publications

  • Parallel ADMM for robust quadratic optimal resource allocation problems

    ACC

    Developed a novel robust GPU based optimal resource allocation algorithm using highly
    parallelisable machine learning techniques (ADMM). The algorithm was developed for
    NVIDIA GPUs (CUDA C/C++) to optimise energy usage in HEVs by learning from past data
    (traffic etc.) to handle large uncertainties in the energy demand. Results showed speed
    up of over 20X using GPUs vs CPUs, making an impractical scenario-based approach
    implementable. Presented an academic paper discussing…

    Developed a novel robust GPU based optimal resource allocation algorithm using highly
    parallelisable machine learning techniques (ADMM). The algorithm was developed for
    NVIDIA GPUs (CUDA C/C++) to optimise energy usage in HEVs by learning from past data
    (traffic etc.) to handle large uncertainties in the energy demand. Results showed speed
    up of over 20X using GPUs vs CPUs, making an impractical scenario-based approach
    implementable. Presented an academic paper discussing algorithm and results at the
    American Control Conference 2019

    See publication

Projects

  • Deep learning models on the web

    - Present

    Please check out my website (qureshizawar.github.io/#demo) if you would like to try out some of the deep
    learning models I have built over the years in your own browser!

    See project
  • Supervisory control of Hybrid electric vehicles using machine learning and optimal control

    -

    • Developed a novel robust GPU based optimal resource allocation algorithm using highly parallelisable machine learning techniques (ADMM). The algorithm was developed for NVIDIA GPUs (CUDA C/C++) to optimise energy usage in HEVs by learning from past data (traffic etc.) to handle large uncertainties in the energy demand. Results showed speed up of over 20X using GPUs vs CPUs, making an impractical scenario-based approach implementable. Presented an academic paper discussing algorithm and…

    • Developed a novel robust GPU based optimal resource allocation algorithm using highly parallelisable machine learning techniques (ADMM). The algorithm was developed for NVIDIA GPUs (CUDA C/C++) to optimise energy usage in HEVs by learning from past data (traffic etc.) to handle large uncertainties in the energy demand. Results showed speed up of over 20X using GPUs vs CPUs, making an impractical scenario-based approach implementable. Presented an academic paper discussing algorithm and results at the American Control Conference 2019 (https://arxiv.org/abs/1903.10041)

    See project
  • Recognising vehicles using Convolutional Neural Networks on an android phone

    -

    Utilised Google’s MobileNet to create an image classifier which was trained using
    images of different types of vehicles (cars, buses, trucks etc.) and deployed on an
    android phone using Tensorflow.

Honors & Awards

  • Glaize Brook Prize

    -

Languages

  • English

    Full professional proficiency

  • Urdu

    Native or bilingual proficiency

  • Arabic

    Elementary proficiency

More activity by Zawar

View Zawar’s full profile

  • See who you know in common
  • Get introduced
  • Contact Zawar directly
Join to view full profile

Other similar profiles

Explore collaborative articles

We’re unlocking community knowledge in a new way. Experts add insights directly into each article, started with the help of AI.

Explore More

Others named Zawar Qureshi

Add new skills with these courses