Modulbeschreibung
AI Foundations
Kurzzeichen:
Durchführungszeitraum:
ECTS-Punkte:
Lernziele:
Methods and applications of artificial intelligence have become an important part of computer science. This module deals with basic concepts from mathematics and computer science. The students learn to:
- process and analyze data using Python
- handle different types of data and coding techniques (e.g. one-hot)
- formulate and train a suitable regression model for a given data
- formulate the training process as an optimization problem and solve it with an iterative algorithm.
- solve specific problems using selected algorithms from supervised and unsupervised learning domains
- describe the quality of a training process qualitatively and quantitatively and learn to generalize the model.
- employ a given AI service in their own applications.
Verantwortliche Person:
Standort (angeboten):
Empfohlene Module:
Zusätzlich vorausgesetzte Kenntnisse:
This module is taught in English. Most of the AI Literature is in English. An intermediate level of English proficiency is recommended. The students are free to write reports in German or English. The exam questions will be in English, the students are free to write answers in German or English.
Skriptablage:
Modultyp:
Bemerkungen:
The lecture will be streamed and recorded.
ECTS-Punkte pro Kategorie
Modulbewertung
Bewertungsart:
Leistungsbewertung
Während der Prüfungssession:
Während des Semesters:
a software project with a short report
Bewertungsart:
Gewichtung:
Software project 40%
written exam 60%
Bemerkungen:
Kurse in diesem Modul
AI Foundations
Kurzzeichen:
Lernziele:
Plan und Lerninhalt:
The students learn and apply the basics of machine learning. The theoretical and mathematical foundations required to understand the machine learning models are taught during this course. During the semester, students develop an AI-supported application. The aim is to integrate existing AI components (e.g. Dialogflow) into an application. The students shall submit a technical report of the project and the report counts towards the final course grade. The course covers the following topics in the lectures and exercise sessions:
- Mathematics and data processing with Python (for example, scipy, numpy, pandas, seaborn, sklearn, and similar packages)
- Preprocessing: data cleansing, standardization, encoding, and feature engineering
- Linear, Polynomial, and Logistic Regression
- Optimization with Gradient Descent (Stochastic, Batch)
- Loss, overfitting, underfitting, regularization, bias/variance, and cross validation
- Selected algorithms of supervised and unsupervised learning (for example for classification and clustering of data)
- Basic concepts of artificial neural networks.
- "AI as a Service": Use of an AI API (e.g. Dialogflow)
Unterrichtssprache:
Bibliographie:
Kursart:
(Durchführung gemäss Stundenplan)