Foundations and Core Concepts of PyTorch

About this course

Updated in May 2025. This course now features Coursera Coach! A smarter way to learn with interactive, real-time conversations that help you test your knowledge, challenge assumptions, and deepen your understanding as you progress through the course. In this comprehensive course, you'll embark on a journey through the foundational elements and core concepts of PyTorch, one of the most popular deep learning frameworks. Starting with a detailed overview and system setup, you'll be guided through installing and configuring your environment to ensure a smooth learning experience. The course then transitions into the basics of machine learning and artificial intelligence, laying the groundwork for more advanced topics. As you delve deeper, you'll explore the intricacies of deep learning, including model performance, activation and loss functions, and optimization techniques. Each module builds on the last, gradually increasing in complexity. You'll learn to construct neural networks from scratch, understanding every component from data preparation to the backpropagation process. This hands-on approach ensures you not only grasp theoretical concepts but also gain practical skills in building and training your models. The course culminates in a detailed look at PyTorch-specific modeling. You will work on real-world exercises, such as implementing linear regression and hyperparameter tuning, using PyTorch’s powerful features. By the end, you'll be well-equipped to tackle complex deep learning problems, confident in your ability to utilize PyTorch effectively for your AI and machine learning projects. This course is ideal for tech professionals, data scientists, and AI enthusiasts looking to master PyTorch for deep learning. Prerequisites include prior experience in Python and a basic understanding of machine learning concepts.

Course objectives

• provide a complete overview of PyTorch setup
• develop skills in building deep learning models
• prepare students to tackle complex deep learning challenges