https://github.com/changkun/ws-18-19-deep-learning-tutorial

Deep Learning and Artificial Intelligence Tutorial @ LMU WS 2018/19
https://github.com/changkun/ws-18-19-deep-learning-tutorial

artificial-intelligence convolutional-neural-networks deep-learning generative-adversarial-network markov-decision-processes recurrent-neural-networks reinforcement-learning representation-learning

Last synced: 9 months ago
JSON representation

Deep Learning and Artificial Intelligence Tutorial @ LMU WS 2018/19

• Host: GitHub
• URL: https://github.com/changkun/ws-18-19-deep-learning-tutorial
• Owner: changkun
• License: mit
• Created: 2018-09-09T13:58:33.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2019-02-01T16:39:21.000Z (over 7 years ago)
• Last Synced: 2025-04-01T08:11:43.188Z (about 1 year ago)
• Topics: artificial-intelligence, convolutional-neural-networks, deep-learning, generative-adversarial-network, markov-decision-processes, recurrent-neural-networks, reinforcement-learning, representation-learning
• Language: Jupyter Notebook
• Homepage: https://changkun.github.io/ws-18-19-deep-learning-tutorial/
• Size: 24.3 MB
• Stars: 14
• Watchers: 1
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# "Deep Learning and Artificial Intelligence" Tutorial

Deep Learning and Artificial Intelligence Tutorial @ LMU WS 2018/19 

> University of Munich, Winter Semester 2018/19, [Course Homepage](http://www.dbs.ifi.lmu.de/cms/studium_lehre/lehre_master/deep1819/index.html)

>

> - **Responsible Professor**: [Prof. Dr. Matthias Schubert](http://www.dbs.ifi.lmu.de/cms/personen/professoren/schubert/index.html)

> - **Lecturers**: Dr. Florian Büttner, Dr. Markus Geipel, Pankaj Gupta, Dr. Denis Krompass, [Prof. Dr. Matthias Schubert](http://www.dbs.ifi.lmu.de/cms/personen/professoren/schubert/index.html), Dr. Sigurd Spieckermann, [Prof. Dr. Volker Tresp](http://www.dbs.ifi.lmu.de/cms/personen/professoren/tresp/index.html)

> - **Assistants**: Sebastian Schmoll, Sabrina Friedl

> - **Tutor**: [Changkun Ou](https://changkun.de)

>

> Time: Monday, 2pm-4pm or 4pm-6pm.

## Tutorial sessions

- 2018.10.22 **Week 1**: Python Introduction

  - [Jupyter Notebook: Python introduction](week1/py_intro_self.ipynb)

- 2018.10.29 **Week 2**: Derivative, Jacobian Matrix, Mean Square Error

  - [Exercise solution: Manuscript](week2/manuscript.pdf)

- 2018.11.05 **Week 3**: Computational Graph, Computational Gradient Graph, Backpropagation (BP), Gradient Vanishing & Exploding Problem

  - [Exercise solution: Manuscript](week3/manuscript.pdf)

  - [Jupyter Notebook: Computational graph numpy implementation](week3/comp_graph.ipynb)

- 2018.11.12 **Week 4**: Convolution, Cross-correlation, ConvLayer and ConvNet

  - [Exercise solution: Manuscript](week4/manuscript.pdf)

  - [Jupyter Notebook: Cross-correlation numpy implementation](wee4/crosscor.ipynb)

  - [Jupyter Notebook: Tensorflow Introduction, CNN, Inception](week4/tf_cnn_inception.ipynb)

- 2018.11.19 **Week 5**: Backpropagation through Time (BPTT), Gradient Vanishing/Exploading in RNN, LSTMs, CIFAR10

  - [Exercise solution: Manuscript](week5/manuscript.pdf)

- 2018.11.26 **Week 6**: Statistic Uncertainty, Evidence Lower Bound, Metropolis-Hastings Algorithm, LSTM

  - [Exercise solution: Manuscript](week6/manuscript.pdf)

  - [Jupyter Notebook: Metropolis-Hastings Algorithm](week6/mha.ipynb)

  - [Jupyter Notebook: LSTM tensorflow implementation](week6/lstm.ipynb)

- 2018.12.03 **Week 7**: Local and distributed representation, Autoencoders, Restricted Boltzmann Machines

  - [Exercise solution: Manuscript](week7/manuscript.pdf)

  - [Jupyter Notebook: Autoencoder](autoencoder.ipynb)

  - [Jupyter Notebook: RBM](rbm.ipynb)

- 2018.12.10 **Week 8**: Tooling, PyTorch Introduction

  - [Exercise solution: text](week8/solution.md)

  - [Jupyter Notebook: PyTorch Introduction](week8/torch.ipynb)

- 2018.12.17 **Week 9**: Variational Autoencoder, GANs

  - [Exercise solution: Manuscript](week9/manuscript.pdf)

  - [Jupyter Notebook: Variational Auto-Encoder](week9/vae.ipynb)

- 2019.01.07 **Week 10**: Markov Reward Process, Markov Decision Process and Policy Iteration

  - [Exercise solution: Manuscript](week10/manuscript.pdf)

  - [Jupyter Notebook: Markov Decision Process](week10/mdp.ipynb)

- 2019.01.14 **Week 11**: Model-free Reinforcement Learning, Temporal Difference Learning, Q-Learning and SARSA

  - [Exercise solution: Manuscript](week11/manuscript.pdf)

  - [Jupyter Notebook: Model-free RL: Q-Learning and SARSA](week12/rl.ipynb)

- 2019.01.21 **Week 12**: Value Function Approximation, Baird’s Counterexample and Montain Car benchmark

  - [Exercise solution: Manuscript](week12/manuscript.pdf)

  - [Exercise solution: Baird's counterexample](week12/ex12-2.ipynb)

  - [Exercise solution: Q-learning in Montain Car](week12/qlearn.ipynb)

- 2019.01.28 **Week 13**: Policy Gradients and Actor Critic Learning

  - [Exercise solution: Manuscript](week13/manuscript.pdf)

  - [Exercise solution: Policy gradient with baseline](week13/ex13-3.ipynb)

- 2019.02.04 **Week 14**: Knowledge Graphs in AI

  - No tutorial

## References

- [LMU "Machine Learning" Tutorial Materials](https://github.com/changkun/ss18-machine-learning-tutorial)

## License

MIT & CC-BY 4.0 Copyright © 2018-2019 [Ou Changkun](https://changkun.de)