Name: Mohamed Ragab
Type: User
Company: Center for Frontier AI Research, A*STAR
Bio: Motivated researcher in Computer Science and Engineering with a strong mastering of mathematical theories. Diverse background in medical imaging techniques
Location: Singapore
Blog: https://mohamed-ragab.netlify.app/
Mohamed Ragab's Projects
Implementation of the work: "ADAST: Attentive Cross-domain EEG-based Sleep Staging Framework with Iterative Self-Training"
This is an implementation of single source multiple target domain adaptation for fault diagnosis
Proposed ATS2S model for C-MAPSS dataset.
implementing "recurrent attentive neural processes" to forecast power usage (w. LSTM baseline, MCDropout)
A collection of AWESOME things about domian adaptation
This is a github repository for Adversarial transfer learning with constrastive coding for time series regression problem.
Conditional Contrastive Domain Generalization For Fault Diagnosis
Deep learning course CE7454, 2018
The standard data-centric AI package for data quality and machine learning with messy, real-world data and labels.
Official repository for CMU Machine Learning Department's 10732: Robustness and Adaptivity in Shifting Environments
Contrastive Predictive Coding for Automatic Speaker Verification
Domain Adaptation Papers and Code
Code release for Discriminative Adversarial Domain Adaptation (AAAI2020)
List of useful data augmentation resources. You will find here some not common techniques, libraries, links to GitHub repos, papers, and others.
Data Science Roadmap from A to Z
Code released for the paper "Deep Learning Algorithms for Rotating Machinery Intelligent Diagnosis: An Open Source Benchmark Study".
Contains code for the NeurIPS 2019 paper "Practical Deep Learning with Bayesian Principles"
PyTorch Lightning + Hydra. A very user-friendly template for rapid and reproducible ML experimentation with best practices. ⚡🔥⚡
Code for reproducing experiments in "Improved Training of Wasserstein GANs"
A cross-platform, linkable library implementation of Git that you can use in your application.
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
Companion webpage to the book "Mathematics For Machine Learning"