\( \newcommand{\vw}{\mathbf{w}} \newcommand{\vx}{\mathbf{x}} \newcommand{\vt}{\mathbf{t}} \newcommand{\vy}{\mathbf{y}} \newcommand{\vz}{\mathbf{z}} \newcommand{\vq}{\mathbf{q}} \newcommand{\vk}{\mathbf{k}} \newcommand{\vv}{\mathbf{v}} \newcommand{\vc}{\mathbf{c}} \newcommand{\vp}{\mathbf{p}} \newcommand{\vh}{\mathbf{h}} \newcommand{\vmu}{\boldsymbol{\mu}} \newcommand{\vsigma}{\boldsymbol{\sigma}} \newcommand{\vepsilon}{\boldsymbol{\epsilon}} \newcommand{\R}{\mathbb{R}} \newcommand{\E}{\mathbb{E}} \newcommand{\norm}[1]{\lVert #1 \rVert} \newcommand{\given}{\,\vert\,} \)

Deep Learning

Lecture Slides

Kasemsit Teeyapan

Department of Computer Engineering, Chiang Mai University · Instructor: Kasemsit Teeyapan Shared across 261459 Deep Learning and 261795 Selected Topics in Computational Intelligence Click a topic to open its slides (press f fullscreen · o overview · s speaker notes · b chalkboard)

⚠️ Note: This material is still under review, revision, and reordering — it may contain errors or change without notice. Please use discretion when citing it.

# Topic
0 Introduction — The Deep Learning Revolution
1 Mathematical Foundations — Probability & Information Theory
2 Linear Regression — Single-layer Networks
3 Classification — Single-layer Networks
4 Statistical Learning & Generalization
5 Deep Neural Networks
6 Gradient Descent
7 Backpropagation
8 Regularization
9 Convolutional Networks
10 Attention & Transformers
11 Representation Learning — Self-Supervised Learning
12 Generative Models
13 Language Models — GPT & BERT
14 Scaling & Modern AI Systems
15 Trustworthy AI — Calibration & Uncertainty
16 Distribution Shift — OOD Generalization
17 Architectural Building Blocks
18 Computer Vision Tasks — Detection & Segmentation
19 Latent Variable Models & EM — Clustering, GMMs
20 Sampling: MCMC & Langevin — Metropolis–Hastings, Langevin

Attribution — Some material is adapted from Bishop & Bishop, Deep Learning: Foundations and Concepts (Springer, 2024), and some figures are taken from the book for educational use only. The full book is freely available from the authors at bishopbook.com