hamedhemati / ml2022-lab Goto Github PK

Welcome to our 8,860,1.00 elective course Machine Learning, taught by Prof. Dr. Damian Borth.

Lectures and hands-on lab courses alternate to provide a better learning experience in this course. The lab course materials for Python programming, Machine Learning, and Deep Learning are available and accessible through this repository.

The the lab content is based on Python, Jupyter Notebook, and PyTorch. The lab notebooks are developed and maintained by the course TA's Marco Schreyer, Konstantin Schuerholt, and Linus Scheibenreif.

Happy Coding!

• Lectures: Mondays 2:15-3:45PM CET, Zoom links are posted on Canvas.
• Labs: Mondays 4:15-5:45PM CET, Zoom links are posted on Canvas.
• Zoom Videos: Will be posted on Canvas shortly after each lecture/lab (unfortunately only accessible to enrolled HSG students).
• Labs Office Hours: Tuesdays 2:00-3:00PM CET, please send us a corresponding invitation via mail.
• Announcements: All course-related announcements and questions will happen on Canvas.

This table lists all lab session and coding challenge session incl. the launchers of the corresponding notebooks. In order to start the notebooks in the respective cloud environment just click on the to corresponding launchers. We aim to upload each lab notebook the day before the lab respectively.

Date	Lab	Content	CoLab Notebook Launchers	MyBinder Notebook Launchers
< Mon, Feb. 28	-	Python 101: Introduction to Python and Jupyter
< Mon, Feb. 28	-	Python 102: Python Data Types and Containers
< Mon, Feb. 28	-	Python 103: NumPy, Pillow, and Matplotlib
Mon, Feb. 28	Lab 1	Support Vector Machines (SVMs) & MNIST
Mon, Mar. 07	Lab 2	Artificial Neural Networks (ANNs) & MNIST
Mon, Mar. 14	Lab 3.1	Convolutional Neural Networks (CNNs) & CIFAR10
Mon, Mar. 14	Lab 3.2	Residual Neural Networks ResNets
Mon, Mar. 21	Lab 4.1	Trend-Following Trading & Nasdaq
Mon, Mar. 21	Lab 4.2	Recurrent Neural Networks (RNNs) & Nasdaq
Mon, Mar. 28	CC 1	Coding Challenge - Kick-Off
-	-	Semester Break - Happy Easter!	-	-
Mon, Apr. 25	Lab 5	Autoencoder Neural Networks (AENs) & Accounting
Mon, May 02	CC 2	Coding Challenge - Mid-Term	-	-
Mon, May 16	Lab 6	Reinforcement Learning
Mon, May 09	Lab 7	Generative Adversarial Networks (GANs) & Fashion MNIST
Mon, May 23	CC 3	Coding Challenge - Submission	tba	tba

This table lists all coding challenge notebooks:

Date	Content	CoLab Notebook	MyBinder Notebook
Mon, Mar. 28	Kickstarter Notebook

This is probably the easiest way to run a Notebook in your web browser: just click on the binder badge next to the Notebooks below, and off you go. Binder is a service that lets you run Jupyter Notebooks in their cloud at no charge. There is no registration and no login required. However, keep in mind that you cannot save any data or your Notebook file in the cloud (you can save them on your computer, though). Also, starting a binder Notebook can take quite some time, but the performance during runtime is good. For more information, please refer to the Binder documentation.

Similar to binder, you just have to click the Colab badge next to the Notebooks below. All you need is a Google login (e.g., your login information for gmail) and you can use this service at no charge. Two advantages of Colab are that (1) you can save your Notebooks directly into your Google Drive and read data from there, and (2) Google provides you with some limited GPU capabilities free of charge (this will be an interesting feature for the coding challenge.)

If you prefer to run Notebooks locally on your computer, you will need to install Python. If you choose to do so, we recommend to install Anaconda Python, a package that combines the latest version of Python with the most common supplemental modules for data science and machine learning, as well as a Jupyter Notebook server that runs on your computer locally. Anaconda installers are available for the most common operating systems, as well as some detailed installation guides.

If you need help running Python and/or Jupyter Notebooks, please don't hesitate to contact us (see below)!

Please use the Canvas forum for course related questions. For external enquiries, emergencies, or personal matters that you don't wish to put in a forum post, you can email us via: aiml (minus) teaching ( dot ) ics ( at ) unisg ( dot ) ch.