Data Science Foundations
1 Week
Skills Gained
- Data preparation, transformation & cleaning
- Exploratory data visualization tools
- SQL & database management
- Python for data manipulation & analysis
Learning Outcomes
You will discover the Data Science lifecycle and explore its different aspects in detail. You will also learn the basics of databases, different data types you will encounter in your study, and different treatment methods for data.
Machine Learning Foundations
2 Weeks
Skills Gained
- Supervised & unsupervised machine learning algorithms
- Model selection & design
- Core ML concepts using real datasets
- Intro to Scikit-learn
Learning Outcomes
You will focus on understanding what a machine learning algorithm is composed of, get introduced to the most popular algorithms and explore their mathematical formulations, and be able to select the best model to build and train on different real-world problems.
Statistical Model Validation & Testing
1 Week
Skills Gained
- Model evaluation metrics & improvement
- Statistical hypothesis testing
- Performance tuning techniques
Learning Outcomes
You will discover common mistakes and mishaps in evaluation of machine learning methods. You will learn different evaluation criteria as well as statistical methods that guarantee your model comparisons are accurate and statistically supported.
Neural Networks & Deep Learning
1 Week
Skills Gained
- Architecture & backpropagation principles
- Keras implementation in Python
- Improving deep learning model performance
Learning Outcomes
You will learn about neural networks’ mathematical foundations and why neural networks have brought about great advancements to the field of Machine Learning. You will get introduced to deep learning libraries in Python and discover techniques for improving deep learning models’ performance.
Deep Learning in Advanced Data Types
2 Weeks
Skills Gained
- Data processing practices for images, text, and time-series
- Convolutional neural networks design and implementation practices
- Recurrent neural networks design and implementation practices
Learning Outcomes
You will learn about new deep learning architectures suitable for different data types. You will understand what makes these data types unique and why there is a need to make use of advanced deep learning designs. You will explore foundations of the Computer Vision, Natural Language Processing, and Time-series signals fields.
Transformers & Large Language Models
1 Week
Skills Gained
- Gain a deep understanding of Transformers in NLP
- Acquire knowledge about the application of Transformers in the field of Computer Vision
- Proficiency in training and fine-tuning large language models
- Master prompt engineering to effectively interact with large language models
Learning Outcomes
You will gain a comprehensive understanding of LLMs and Transformer architectures, crucial in the evolution of NLP. Including insights into the Transformer model’s unique self-attention mechanism, distinctions from previous architectures. You will acquire practical skills in fine-tuning models, employing techniques like LoRA and QLoRA, enhancing their ability to optimize performance.
Machine Learning in Production
2 Week
Skills Gained
- Define & scope ML problems
- Deploy Cloud-based ML deployment & monitoring
- Deploy & maintain model
- Communicate results across teams
Learning Outcomes
Now that your foundation is solid, you will explore machine learning in practice: what are the challenges commonly faced when these models are deployed in real-world and how to overcome them, what are some best practices to abide by, and what are tools that can help you scale to real-world implementations.
Learn how ZAKA is transforming the AI landscape in MENA
English 
Arabic