Deep Learning

Units

1. 1

   Introduction to Neural Networks

   Understand how neural networks learn: the architecture, the mathematics of training, and the practical tools that turn theory into working models. The foundation for every unit that follows.

   →
2. 2

   Computer Vision

   Learn how machines process and interpret visual information, from classical feature extraction through CNNs, detection, segmentation, and evaluation, to the modern architectures defining the current state of the art.

   →
3. 3

   Natural Language Processing

   Explore how machines process and generate language, from bag-of-words representations through attention and transformers, to practical implementation, LLMs, RAG, and multimodal models.

   →
4. 4

   Recommendation Systems

   Build intuition for how modern recommendation systems work: the algorithms behind collaborative filtering and matrix factorization, deep learning approaches, and the engineering tradeoffs that matter in production.

   →
5. 5

   Generative AI

   Master the three dominant generative frameworks — GANs, VAEs, and diffusion models — from first principles through practical application, including architecture selection, evaluation, and the failure modes that surface in deployed systems.

   →

About

This workbook was created and is maintained by Dr. Brinnae Bent at Duke University for AIPI 540: Deep Learning Applications.

If you need a refresher on Data Science fundamentals, check out my Data Science Workbook.

Licensed under CC BY-SA 4.0.