Hands-On Deep Learning with MIT OpenCourseWare

About this path

This learning path is built from MIT OpenCourseWare's 15.773 Hands-On Deep Learning Spring 2024 lectures, taught by Rama Ramakrishnan. It is designed for learners who already know Python and have basic machine learning knowledge (training/validation/testing, overfitting/underfitting, regularization). The path moves from training deep neural networks on tabular data, to building convolutional networks for images, to transformers and self-supervised learning for text, and finally to generative AI including LLMs, RAG, and text-to-image models. Each section includes one or two lectures, and you can follow the video order within each section. The full course materials are available on MIT OpenCourseWare.

What you will learn

• Understand the basics of deep neural networks and how to train them effectively.
• Build and apply convolutional neural networks for image and video processing.
• Use transfer learning and fine-tuning for computer vision tasks.
• Understand embeddings and transformers for natural language processing.
• Explore self-supervised learning and its role in modern NLP.
• Learn about large language models, retrieval augmented generation, and parameter-efficient fine-tuning.
• Gain familiarity with text-to-image generative models.

Who this is for

Self-paced learners who want a clear free path with creator-credited YouTube lessons.

Curriculum