de | en

Machine Learning: Methods and Tools

Module EI71040

This Module is offered by Chair of Electronic Design Automation (Prof. Schlichtmann).

This module handbook serves to describe contents, learning outcome, methods and examination type as well as linking to current dates for courses and module examination in the respective sections.

Module version of WS 2019/20 (current)

There are historic module descriptions of this module. A module description is valid until replaced by a newer one.

Whether the module’s courses are offered during a specific semester is listed in the section Courses, Learning and Teaching Methods and Literature below.

available module versions
WS 2019/20WS 2018/9

Basic Information

EI71040 is a semester module in English language at Master’s level which is offered every semester.

This Module is included in the following catalogues within the study programs in physics.

  • Catalogue of non-physics elective courses
Total workloadContact hoursCredits (ECTS)
150 h 60 h 5 CP

Content, Learning Outcome and Preconditions

Content

**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;

Learning Outcome

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.

Preconditions

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

Courses, Learning and Teaching Methods and Literature

Courses and Schedule

Learning and Teaching Methods

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.

Media

Black/white board, beamer, computer, software.

Literature

* 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

Module Exam

Description of exams and course work

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.

Exam Repetition

There is a possibility to take the exam in the following semester.

Top of page