Machine Learning: Methods and Tools

**Lecture, Exercises and hands-on lab**
Digital transformation and machine learning;
Python, standard libraries, SciPY and NumPy;
Theory of Machine Learning, Regularization, Errors and Noise;
Data analysis, pre-processing, visualization:
Introduction to algorithms of Machine Learning;
Introduction to Feedforward Neural Networks and Convolutional Neural Networks, RNNs, LSTM;
Training of neural networks, attention models, unsupervised learning, reinforcement learning, hyper-parameter optimization;

After participating in the module, the student knows and masters in a differentiated way basic methods and algorithms of machine learning. He/she is able to apply them to engineering in microelectronic design tasks. In addition, he/she is able to become familiar with other areas of machine learning. He/she knows the embeddedness of Machine Learning in the digital transformation and is aware of the social opportunities and risks.

Knowledge in Linear Algebra, Analysis and Statistics, Proficiency in a programming language, e.g., C, C++, Java

Lecture and exercise are designed as interactive frontal lessons. By projection of slides and blackboards, the algorithms to be taught are developed step by step and with the participation of the learners in the lecture. In the exercise, work instruction takes place by examples and joint calculation of tasks. Algorithms are used as examples and repeatedly.
The students prepare for the lecture and exercise by studying the documents and prepare the material they have taken through self-study. Own literature searches are part of self-study.
In a hands-on lab part, the students are given practical problems in the field of microelectronics for independent solving. The tasks set include practical applications of machine learning in the automatic design of integrated circuits and systems.

Black/white board, beamer, computer, software.

* Maschinelles Lernen - Grundlagen und Algorithmen in Python, Frochte J., Hanser Fachbuch
* Einführung in Python 3, Klein B., Hanser Fachbuch.
* Learning from Data, Abu-Mostafa, Yaser S. et al., AMLBook 2012.
* Deep Learning, Goodfellow, Ian et al, The MIT Press 2016.
* Machine learning: A probabilistic perspective, Murphy, Kevin P., The MIT Press 2013

The exam is in written form with closed book policy and takes 60 minutes.
The understanding and knowledge in the field of machine learning is examined. Furthermore, the ability to use machine learning methods to formulate and solve design problems in microelectronics will be tested on the basis of manual calculation tasks as well as tasks from the lecture-accompanying lab.
Finally, with background questions, the ability to solve further engineering tasks by means of machine learning is examined.