딥러닝 (Deep Learning)

강의실: 공학 7관 xxx호
Textbooks
- Antonio Torralba, Phillip Isola, William T. Freeman, Foundations of Computer Vision, MIT Press, 2024, https://mitpress.ublish.com/book/foundations-of-computer-vision-1, [book]
- Christopher M. Bishop and Hugh Bishop, Deep learning: Foundations and concepts, Springer, 2023, [book]
- I. Goodfellow, Y. Bengio, A. Courville, Deep learning, MIT Press, 2016 [book]
Textbooks (additional)
- Kevin Patrick Murphy, Machine Learning: a Probabilistic Perspective, MIT Press, 2012 [link]
- Kevin Patrick Murphy, Probabilistic Machine Learning: An instruction, MIT Press, 2022 [link]
- Kevin Patrick Murphy, Probabilistic Machine Learning: An advanced topic, MIT Press, 2023 [link]
- Richard S. Sutton and Andrew G. Barto, Reinforcement Learning: An Introduction, MIT Press, 1998 [link] [2nd_edition]
- D. Koller and N. Friedman, Probabilistic Graphical Models: Principles and Techniques, MIT Press, 2009 [book]
References
- Matrix cookbook pdf
- Matrix differential calculus with applications in statistics and econometrics pdf
- Matrix differentiation pdf
- The Matrix Calculus You Need For Deep Learning pdf
- Old and New Matrix Algebra Useful for Statistics pdf
- Python notebooks for PRML text book [link]
- Deep learning Lecture at MIT [link]
- Deep learning Lecture 2024 at MIT [link]
- TinyML and Efficient Deep Learning Computin at MIT [link]
- Deep learning Lecture at CMU [link]
- ML and Data Mining Lecture at U. Toronto [link]

Chapter 1: Introduction [pdf]
Chapter 2: Backpropagation [pdf]
Chapter 3: Approximation theory [pdf]
Chapter 4: Convolutional networks [pdf]
Chapter 5: Graph neural networks [pdf]
Chapter 6: Transformers [pdf]
Chapter 7: Memory [pdf]
Chapter 8: Representation learning -- reconstruction-based [pdf]
Chapter 9: Representation learning -- similarity-based [pdf]
Chapter 10: Generative models -- basics [pdf]
Chapter 11: Generative models -- representation learning meets generative modeling [pdf]
Chapter 12: Generative models -- conditional models [pdf]
Chapter 13: Generalization (OOD) [pdf]
Chapter 14: Transfer learning -- models [pdf]
Chapter 15: Transfer learning -- data [pdf]
Chapter 16: Large language models [pdf]
Chapter 17: Scaling laws [pdf]
Chapter 18: Inference methods for deep learning [pdf]
Special topics 1: Retrieval augmented large language models
Chapter x: Recurrent neural networks
Chapter x: Graph neural networks
Chapter x: Transformers
Chapter x: Neural architecture search
Chapter x: Diffusion models
Chapter x: Large language models
Chapter x: Efficient LLM: prunning
Chapter x: Efficient LLM: quantization
Chapter x: Long-context LLM