Catalog

Hands-On Deep Learning

Sloan School of Management MIT CC BY-NC-SA 4.0 11 lectures

This is a fast-paced introduction to deep learning with an emphasis on developing a practical understanding of how to build models to solve complex problems involving unstructured data. Topics include the basics of deep neural networks and how to set up and train them, convolutional networks to process images and videos, transformers for natural language processing, generative large language models (such as ChatGPT), and text-to-image models (such as Midjourney). Prior familiarity with Python and fundamental machine learning concepts (such as training/validation/testing, overfitting/underfitting, and regularization) is required.

Syllabus

  1. 1 1: Introduction to Neural Networks and Deep Learning; Training Deep NNs
  2. 2 2: Training Deep NNs (cont.); Introduction to Keras/Tensorflow; Application to Tabular Data
  3. 3 3: Deep Learning for Computer Vision – Building Convolutional Neural Networks from Scratch
  4. 4 4: Deep Learning for Computer Vision – Transfer Learning and Fine-Tuning; Intro to HuggingFace
  5. 5 5: Deep Learning for Natural Language – The Basics
  6. 6 6: Deep Learning for Natural Language – Embeddings
  7. 7 7: Deep Learning for Natural Language – Transformers
  8. 8 8: Deep Learning for Natural Language – Transformers, Self-Supervised Learning
  9. 9 9: Generative AI – Large Language Models (LLMs) and Retrieval Augmented Generation (RAG)
  10. 10 10: Generative AI – Adapting LLMs with Parameter-Efficient Fine-Tuning
  11. 11 11: Generative AI – Text-to-Image Models

Course materials