Learning objectives
<br />Objectives<br /> <br />The course aims at providing students with the basic concepts regarding adaptive methods, often biologically-inspired, which allow computer emulation of learning-from-examples processes, and are used to optimize/design solutions to real-world problems.
Prerequisites
- - -
Course unit content
<br />
Program<br />
<br />
Biological and automatic learning.<br />
Review of the main classical machine-learning techniques <br />
Soft Computing techniques<br />
Neural Networks<br />
Evolutionary Computation<br />
Genetic Algorithms<br />
Genetic Programming<br />
Swarm Intelligence<br />
Examples of real-world applications<br />
<br />
<br />
Laboratory activities<br />
<br />
Practical assignments in laboratory on real-world examples
Full programme
- - -
Bibliography
<br />Suggested textbook<br /> <br />Teaching material available online and other material that will be distributed and published online all through the course.<br /> <br /> <br />Additional textbooks<br /><br />Tettamanzi Tomassini - Soft computing : integrating evolutionary, neural, and fuzzy systems. Springer, 2001 <br /><br />Haykin - Neural Networks. US Imports & PHIPEs, 1998 <br /><br />Eiben - Smith, Introduction to Evolutionary Computing, Springer, 2003 <br /><br />Banzhaf Nordin Keller Francone - Genetic Programming, Morgan Kaufmann, 1998 <br />
Teaching methods
<br />Examination methods<br /> <br />Intermediate evaluation of the lab assignments and final project
Assessment methods and criteria
- - -
Other information
- - -