Module 3

Deep Learning with PyTorch

(MUST) Prerequisite for Python

"파이썬 입문", in 프로그래머스 (in Korean)

Python Setup (download)
Python Tutorial in 10 Minutes (download)
PyTorch Tutorial in 10 Minutes (download)
You can also download the codes on Github.

Topics

Materials and Codes

1st Session

(8/6, 14:00~15:30)

(Lecture) Deep Learning 101 - Part 1.

Slide download (pdf / ppt)

(Optional)

Tutorial on Deep Learning, presented at INFORMS CIST 2017 (Prof. Param Vir Singh, Carnegie Mellon University) (Link)
Lecun, Y., Bengio, Y. and Hinton, G., 2015. Deep Learning. Nature, 521, pp.436-444.
Jordan, M.I. and Mitchell, T.M., 2015. Machine Learning: Trends, Perspectives, and Prospects. Science, 349(6245), pp.255-260.
Wang, H., Raj, B. and Xing, E.P., 2017. On the Origin of Deep Learning. arXiv:1702.07800.

2nd Session

(8/9, 14:00~15:30)

(Lecture) Deep Learning 101 - Part 2.

3rd Session

(8/13, 14:00~15:30)

Web Data Extraction

Slide download (pdf / ppt)
Material download (zip)

4th Session

(8/16, 14:00~15:30)

Linear Regression in the PyTorch Way

Neural Network

Slide download (pdf / ppt)
Material download (zip) / Exercise example (zip)

5th Session

(8/20, 14:00~15:30)

Convolutional Neural Network (CNN)

- (Application for NLP) Sentence Classification

Slide download (pdf / ppt)
Material download (zip) / Exercise example (zip)
Kim, Y., 2014. Convolutional Neural Networks for Sentence Classification. In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP).
Lee, D., Hosanagar, K. and Nair, H.S., 2018. Advertising Content and Consumer Engagement on Social Media: Evidence from Facebook. Management Science. forthcoming

(Optional)

CS231n: Convolutional Neural Networks for Visual Recognition, Stanford University (Spring 2017) (videos / slides)

6th Session

(8/23, 14:00~15:30)

Recurrent Neural Network (RNN)

- (Application for NLP) Machine Translation (Sequence-to-Sequence)

Slide download (pdf / ppt)
Material download (zip) / Exercise example (zip)
Park, J. and Kim, J., 2018. Leveraging Machine Learning to Reduce Racial Bias on Online Platforms: A Neural Machine Translation Approach. KAIST Working Paper. (download)

(Optional)

CS224n: Natural Language Processing with Deep Learning, Stanford University (Spring 2017) (videos / slides)

7th Session

(8/27, 14:00~15:30)

Deep Reinforcement Learning

- Deep Q-Network (DQN)

Slide download (pdf / ppt)
Material download (zip) / Exercise example (zip)
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G. and Petersen, S., 2015. Human-Level Control through Deep Reinforcement Learning. Nature, 518(7540), p.529–533.

(Optional)

CS294: Deep Reinforcement Learning, UC Berkeley (Fall 2017) (videos / slides)

8th Session

(8/30, 14:00~15:30)

Leveraging Deep Learning on Your Computer

- Supervised Learning using Amazon Mechanical Turk

- How to Use Cloud-based APIs

- Running Deep Learning on the Cloud (Amazon Web Service)

Slide download (pdf / ppt)
Material download (zip)
Kim, J. and Park, J., 2017. Does Facial Expression Matter Even Online? An Empirical Analysis of Facial Expression of Emotion and Crowdfunding Success. Proceeding of International Conference on Information Systems (ICIS) 2017. (download)

Acknowledgement

My tutorial codes owe largely to the following sources:

Official PyTorch Tutorials (https://pytorch.org/tutorials) - This is a MUST to get familiar with PyTorch!
Simple PyTorch Tutorials Zero to ALL (https://github.com/hunkim/PyTorchZeroToAll)
PyTorch Tutorial for Deep Learning Researchers (https://github.com/yunjey/pytorch-tutorial)
PyTorch로 시작하는 딥러닝 입문 CAMP (https://github.com/GunhoChoi/PyTorch-FastCampus)
Practical PyTorch (https://github.com/spro/practical-pytorch)
DeepNLP models - PyTorch (https://github.com/DSKSD/DeepNLP-models-Pytorch)

Google Sites

Report abuse