I’m TAUIL Abd Elilah, a 26-year-old researcher PHD student in the field of deep learning. I hold a master’s degree in computer science, technical writter at Paperspace, Zindi Ambassador in Morocco, Teaching assistant on various courses (Programming, operating system), Kaggle expert, I have a deep passion for Artificial Intelligence, Data Science, and problem-solving. My journey into the world of data began back in 2018, and ever since, I’ve been dedicated to enhancing my skills. My goal is to use data to make a positive impact on society and the world, and looking for a new challenge.
A leading Moroccan institution offering diverse undergraduate and graduate programs across various disciplines. UAE provides a vibrant campus life with modern facilities, active student clubs and international partnership.
Zindi connects organizations with data scientists to solve Africa’s most pressing challenges. Through crowdsourced problem-solving, talent identification, and skill development, Zindi fosters innovation and unlocks data potential.
Discover insightful articles, tutorials, and guides on AI, ML, deep learning, and more. Learn from expert contributors and stay up-to-date on the latest trends and advancements in the field. Explore innovative applications and unlock new possibilities for your own projects.
2021 - Present Researcher PHD Student - E-Fashion in Deep LearningExtracurricular Activities:
| ||
Master of Science in Computer engineeringTaken Courses:
| ||
Bachelor's degree in Mathematics and Computer ScienceTaken Courses:
| ||
General University Studies Diploma in Mathematics and Computer ScienceTaken Courses:
| ||
2014-2015 Baccalaureate in Mathematical Science |
Make a clean, simple, and readable implementation from scratch of StyleGAN-2 to generate clothes using PyTorch .
Use Machine Learning to detect conditions with measurements of anonymous characteristics. Out of 6,430 data scientists worldwide, I finished 612th on the leaderboard (Top 10%)
Competition on Kaggle. Out of 952 data scientists worldwide, I finished 9th on the leaderboard (Top 1%).
Competition on Kaggle. Out of 1088 data scientists worldwide, I finished 97th on the leaderboard (Top 9%).
Make a clean, simple, and readable implementation from scratch of StyleGAN to generate clothes using PyTorch .
Make a clean, simple, and readable implementation from scratch of ProGAN to generate clothes using PyTorch .
Person segmentation using deep learning approache, PyTorch.
Generate fashion MNIST using deep learning approache, PyTorch.
Competition on Kaggle. Out of 7,573 data scientists worldwide, I finished 141th on the leaderboard (Top 2%).
Use Sentinel 5P data to predict air quality in Kampala for AirQo. Out of 684 data scientists worldwide enrolled, I finished 11th on the leaderboard.
Extract support phrases for sentiment labels. Out of 2225 data scientists worldwide, I finished 43th on the leaderboard (Top 2%).
This course equips you to analyze the challenges of evaluating Generative Adversarial Networks (GANs) and compare them to other generative models. You’ll master the Fréchet Inception Distance (FID) method to assess the fidelity and diversity of GANs, uncover potential biases, and learn to implement cutting-edge techniques associated with the state-of-the-art StyleGANs.
In the third course of the Deep Learning Specialization, you will learn how to build a successful machine learning project and get to practice decision-making as a machine learning project leader. By the end, you will be able to diagnose errors in a machine learning system; prioritize strategies for reducing errors; understand complex ML settings, such as mismatched training/test sets, and comparing to and/or surpassing human-level performance; and apply end-to-end learning, transfer learning, and multi-task learning.
This is the second course of the Deep Learning Specialization, you will open the deep learning black box to understand the processes that drive performance and generate good results systematically. By the end, you will learn the best practices to train and develop test sets and analyze bias/variance for building deep learning applications; be able to use standard neural network techniques such as initialization, L2 and dropout regularization, hyperparameter tuning, batch normalization, and gradient checking; implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence; and implement a neural network in TensorFlow.
This is the first course of the Deep Learning Specialization, you will study the foundational concept of neural networks and deep learning. By the end, you will be familiar with the significant technological trends driving the rise of deep learning; build, train, and apply fully connected deep neural networks; implement efficient (vectorized) neural networks; identify key parameters in a neural network’s architecture; and apply deep learning to your own applications.
Understand and apply Google’s game-changing NLP algorithm to real-world tasks. Build 2 NLP applications.