This course describes the use of neural network models in learning and optimization  e.g., pattern recognition, routing, and prediction. This course is divided into two parts. The first part (3 weeks) provides an introduction to neural networks, focusing on the so-called Hopfield model, its statistical mechanics and optimization algorithms. The second part (4 weeks) provides a more detailed introduction to learning, describing models, algorithms, and applications.

Part 1: An introduction to neural networks: neuroscience, statistics and optimization

  • Neuroscience
  • An example of a neural network: the Hopfield model
  • Statistics and Optimisation (Monte-Carlo methods, simulated annealing)

Part 2: Learning: models, algorithms, and applications

  • Supervised learning: simple perceptrons and layered networks
  • Performance of multilayer perceptrons
  • Unsupervised learning
  • Reinforcement learning
  • Recurrent networks and time series analysis


Student portal page:

External course webpage: None that currently is alive




Published in Courses

In this course, we study humanoid robots, i.e. robots that have an approximately human-like shape. Such robots form an important special case of the autonomous robots studied in the course Autonomous agents. For example, unlike wheeled robots, a walking humanoid robot is (in principle) able to climb stairs and is also, in general, better adapted (than a wheeled robot) to environments designed for people.

The course begins with two weeks of lectures, during which the theoretical foundations of humanoid robots are explored. The remaining part of the course consists of lab work, during which several different humanoid robots are used for solving a variety of tasks, focusing on human-robot interaction.

Student portal page:

External course webpage:

Published in Courses

Throughout the first year, a seminar series is held in which the students present and discuss recent findings and results reported in the scientific literature. Complex systems science is a large and very heterogeneous research field. When preparing a presentation in the Complex systems seminar course, the students have an opportunity to "dig a little deeper" into a specific area that they find interesting. The students in the class will during the class be listening to 40-50 seminars on different topics, mostly given by their friends in the class but also by the teachers in the program and other guest lecturers. Overall this gives a more fair coverage of complex systems as a field than is possible in the regular classes. In addition the class offers training in a very central skill: oral presentation.

Teacher: Claes Andersson

Teaching Assistants: Erik Edlund, Oskar Lindgren, Vilhelm Verendel

Student portal page:

Course page:


Published in Courses
Page 2 of 2