Teaching language: English
Open for exchange students
Block schedule:
B
Course module 

Credit distribution 

Examination dates 
Sp1 
Sp2 
Sp3 
Sp4 
Summer course 
No Sp 
0100 
Written and oral assignments 
7,5c 
Grading: TH 

7,5c








In programs
TKITE SOFTWARE ENGINEERING, Year 3 (compulsory elective)
TIDAL COMPUTER ENGINEERING, Year 3 (compulsory elective)
MPCAS COMPLEX ADAPTIVE SYSTEMS, MSC PROGR, Year 1 (compulsory)
MPENM ENGINEERING MATHEMATICS AND COMPUTATIONAL SCIENCE, MSC PROGR, Year 2 (elective)
MPSYS SYSTEMS, CONTROL AND MECHATRONICS, MSC PROGR, Year 2 (elective)
Examiner:
Professor
Bernhard Mehlig
Eligibility:
In order to be eligible for a second cycle course the applicant needs to fulfil the general and specific entry requirements of the programme that owns the course. (If the second cycle course is owned by a first cycle programme, second cycle entry requirements apply.)
Exemption from the eligibility requirement:
Applicants enrolled in a programme at Chalmers where the course is included in the study programme are exempted from fulfilling these requirements.
Course specific prerequisites
Sufficient knowledge of Mathematics (analysis in one real variable, linear algebra), basic programming skills.
Aim
Neural networks are distributed computational models inspired by the structure of the human brain, consisting of many simple processing elements which are connected in a network. Neural networks are increasingly used in the engineering sciences for tasks such as pattern recognition, prediction and control. The theory of neural networks is a interdisciplinary field (neurobiology, computer science and statistical physics).
The course gives an overview and a basic understanding of neuralnetwork algorithms.
Learning outcomes (after completion of the course the student should be able to)
understand and explain strengths and weaknesses of the neuralnetwork algorithms discussed in class
determine under which circumstances neural networks are useful in real applications
distinguish between supervised and unsupervised learning and explain the key principles of the corresponding algorithms
efficiently and reliably implement the algorithms introduced in class on a computer, interpret the results of computer simulations
describe principles of more general optimisation algorithms
write wellstructured technical reports in English presenting and explaining analytical calculations and numerical results
communicate results and conclusions in a clear and logical fashion
Content
Introduction to neural networks (McCulloch Pitts neurons, associative memory problem, Hopfield model and Hebb s rule, storage capacity, energy function)
Stochastic neural networks (noise, order parameter, meanfield theory for the storage capacity)
Optimisation
Supervised learning: perceptrons and layered networks (feedforward networks, multilayer perceptrons, gradient descent, backpropagation, conjugategradient methods, performance of multilayer networks)
Unsupervised learning (Hebbian learning, Oja s rule, competitive learning, topographic maps)
Recurrent networks and timeseries analysis (recurrent backpropagation, backpropagation in time
Reinforcement learning
Organisation
Lectures, set homework problems, examples classes.
Webbased course evaluation.
Literature
Lecture notes will be made available. They are based on the course book: Hertz, A. Krogh, and R. G. Palmer, Introduction to the theory of neural computation, AddisonWesely, Redwood City (1991).
Additional reading: S. Haykin, Neural Networks: a comprehensive foundation, 2nd ed., Prentice Hall, New Jersey (1999)
Examination
The examination is based on exercises and homework assignments (100%).