Neural Networks
About
The course gives an overview and a fundamental theoretical understanding of the most important neural net algorithms. These include models of associative memory algorithms for learning from examples (e.g., perceptron learning, back-propagation, temporal difference learning), and models for self-organization. Through comparison with methods from statistics and computer science students can develop an understanding of when neural networks are useful in application problems.
This course is open to
Exchange students at the Faculty of Science and exchange students on a university-wide agreement. Please contact your international coordinator at the University of Gothenburg if you need to know more.
In order to apply for this course you must have successfully completed
a Bachelor's degree in Engineering, Natural or Mathematical sciences of 180 credits including knowledge of Mathematical analysis, Linear algebra and Programming.
English proficiency
Incoming students should have an English level equivalent of B2 or higher as courses and materials, including presentations and exams, will be in English.
To assess your English level, you can use the self-assessment grid for reference: https://europa.eu/europass/en/common-european-framework-reference
Application
Do you want to apply for exchange studies at the University of Gothenburg?