Neelay Shah

Hello! I am Neelay Shah, a final year undergraduate student at Birla Institute of Technology and Science, Pilani. I'm working towards a degree in Electronics and Instrumentation Engineering.

CV  /  Email  /  GitHub  /  Google Scholar  /  Twitter

Centre of Intelligent Robotics, Indian Institute of Information Technology Allahabad
Research intern

  • Used model compression techniques to develop compact multi-modal emotion recognition models for human-robot interaction using deep learning
  • Implemented generative grasping convolutional neural networks (GGCNNs) for robotic grasping
Publications / Preprints
  • A U-Net Image Segmentation Based Approach Improves Photoacoustic Tomographic Image Reconstruction
    Neelay Shah, Manish Bhatt
    Pre-print | Under review

  • KD-Lib: A PyTorch library for Knowledge Distillation, Pruning and Quantization
    Het Shah, Avishree Khare, Neelay Shah, Khizir Siddiqui
    Pre-print | [arXiv] [Code]
Open-source Software
  • KD-Lib
    GitHub / Documentation / Preprint

    An easy to use PyTorch library containing knowledge distillation, pruning, and quantization methods for deep learning models

  • EzFlow
    GitHub / Documentation

    A modular PyTorch library for optical flow estimation using neural networks

Research Projects
  • Ultrasound Image Reconstruction using Deep Learning
    Dr. Manish Bhatt, BITS Pilani Goa

    • Worked on developing an image segmentation approach using deep learning for improving photoacoustic tomographic image reconstruction.

  • Machine Learning for Satellite Navigation
    Digital Communication Lab, BITS Pilani Goa

    • Developed a deep learning pipeline to forecast irregularities in the ionosphere which cause fluctuations in satellite navigation signals
    • Benchmarked machine learning models for classifying multi-path interference in satellite signals

PS: If you have some spare time and are interested, please visit and help amplify this website which lets people picture the impacts of climate change. Also, do take a look at these heart-wrenching climate change statistics. Thanks!

Much gratitude to Jon Barron for the template!