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. Embark on a transformative journey through modern machine learning, computer vision, and generative AI with this comprehensive course. Explore industry-leading techniques like image classification, object detection, and cutting-edge generative models powered by KerasCV and Stable Diffusion. Gain hands-on experience with tools and frameworks that make these advanced topics approachable and actionable. The course begins with the fundamentals of pre-trained models and transfer learning, empowering you to implement and fine-tune image classifiers in Python. From there, dive into object detection, mastering dataset formats, augmentation techniques, and loss functions while leveraging KerasCV for efficient fine-tuning. Next, delve into generative AI with Stable Diffusion, uncovering its architecture, mechanics, and codebase. Learn to create stunning visuals and understand how these models condition on prompts, offering insights into the frontier of AI-driven creativity. Additional modules provide guidance on Python coding, environment setup, and learning strategies, ensuring that learners of all levels can succeed. This course is designed for learners interested in deep learning, computer vision, and AI creativity. A basic understanding of Python and machine learning is recommended. Whether you're a developer, researcher, or enthusiast, this intermediate-level course will elevate your skills and open new horizons in AI innovation.