Name: Mohamed Ayoob
Type: User
Company: Ph.D. (Reading), University of Nottingham
Bio: Artificial Intelligence researcher by day, and a Judo Student by night. I love riding my bicycle. Sometimes I cook. Math is my dope. Pythonista.
Blog: https://ayoob7.github.io
Mohamed Ayoob's Projects
Efficient Augmented Reality for the Web - 60fps on mobile!
This is series of task done for the CERN CMS Muon estimation project
A program to check the size of a GitHub repo before cloning.
An adversarial example library for constructing attacks, building defenses, and benchmarking both
A program to Cluster a set of Coordinate points
Pytorch Implementation of ClusterGAN (arXiv:1809.03627)
Projects attempted in the Reinforcement Degree Nanodegree program
A collection of notebooks and projects done as a part of Udacity's Deep Learning Nanodegree using Pytorch. https://www.udacity.com/course/deep-learning-nanodegree--nd101
A Nanodegree project for Deep Learning - udacity
An Interactive Dictionary
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
This is the research product of the thesis manifold Learning of Latent Space Vectors in GAN for Image Synthesis. This has an application to the research, name a facial recognition system. The application was developed by consulting the FaceNet model.
Must-read papers on graph neural networks (GNN)
Google Research
This Swift Playground is about teaching Hashing Functions to students. I take through Hash Functions from 2 vantage points. They are File Comparisons and Hashed Lookups. These are the 2 ways that Hashing Functions are used.
A library for transfer learning by reusing parts of TensorFlow models.
Templates from PyTorch for Deep Learning Tasks
Traffic Contraception is a system that loads location based data from various different cities to get meaningful insights on traffic modelling and management. I take data handling from 2 vantage points. Visualization and Statistical modelling. Visualization is mandatory before performing machine learning operations or statistical modelling, and visualization help us familiarize with the data. After visualizing the data I modeled the data on statistical models. After modelling statistically the data was visualized on graphs for domain experts and city planners to analyze and make prudent changes to the traffic system. Such changes will have potentials to optimize the traffic flow thereby giving a better commute to load-intensive highways.
Application made for the Visiting Student Research Program at KAUST
Maze Robot game made in the B programming language, using Atelier B and Pro B (Used Visual Studio Code B method plugin to develop)
Neural Symbolic Machines is a framework to integrate neural networks and symbolic representations using reinforcement learning, with applications in program synthesis and semantic parsing.
Open Source Computer Vision Library