للحصول على شهادة
his course, inspired by Stanford CS229: Machine Learning, focuses on the core principles required to build Large Language Models (LLMs) from the ground up. It combines strong mathematical foundations with practical system design concepts used in modern AI development.
You will begin by reviewing essential machine learning concepts such as supervised learning, optimization algorithms, gradient descent, regularization, and probabilistic modeling. The course then connects these foundations to deep learning, neural networks, and transformer architectures that power today’s LLMs.
A major focus is placed on understanding how large-scale models are trained, including data preprocessing, tokenization, scaling laws, distributed training, and evaluation metrics. You will also explore fine-tuning strategies, reinforcement learning approaches, and performance optimization methods used in production AI systems.
By the end of this course, learners will understand both the theoretical foundations and engineering practices required to design, train, and deploy large language models. This course is ideal for advanced students, AI engineers, and researchers seeking a deeper understanding of LLM construction and machine learning theory.