Organisation

Time only SS
Time Thursday, 08.15h-11.30h
Room 136
Credits 2 SWS / 5 ECTS
Exam Lab Work

Announcements

  • First lesson in term SS 23: 16.03.23

Prerequisites for participation

  • Successful completion of the CSM Machine Learning Lecture.

Structure, Contents, Documents

In this lab student-groups must implement selected applications of Machine Learning in particular Deep Learning. All applications must be implemented in Python Jupyter-Notebooks. The Python machine learning libraries scikit-learn, Tensorflow and Keras will be applied.

I recommend to download Anaconda for Python 3.8 or newer. Then a new virtual environment shall be created by conda create -n pia python=3.8 anaconda. In this virtual environment use pip install to install tensorflow, keras, gensim, and other required modules.

Each of the lab-exercises (applications) will be graded. The final grad of the course is the mean of the exercise grades.

New, from term SS21 on is the combination of the lectures PIA and Selected Topics of Deep Learning (STDL). Actually the lab exercises of PIA has been extended and partitioned into these two lectures. As depicted below the first 4 exercises are assigned to PIA, the remaining 4 exercises are assigned to STDL. The 2 modules therefore run consecutively. Students, which like to execute all exercises must register for PIA and STDL. It is also possible to register only for PIA. It is not possible to register only for STDL, because it makes no sense to skip the intro in the first part and start with the 5.th exercise.

PIA in Ilias

Lecture Contents
16.03.2023 Short Introduction and Registration
23.03.2023 Introduction into Tensorflow
30.03.2023 Implementation of GAN for MNIST
06.04.2023 Implementation of GAN for MNIST
13.04.2023 Word Embeddings Transformers
20.04.2023 Word Embeddings Transformers
27.04.2023 RNN Music Generation
04.05.2023 RNN Music Generation
———— —————–
11.05.2023 RL 1: Dynamic Programming
25.05.2023 RL 2: Reinforcement Learning
15.06.2023 RL 3: Deep Reinforcement Learning
22.06.2023 RL 3: Deep Reinforcement Learning
29.06.2023 Graph Neural Networks