Dansk - English
Short version - Full version
Artificial Neural Network (Spring 2005) |
|||
| Course code : | EANN-U01 | ||
| ECTS Credits : | 7,5 | Status : | Optional |
| Revised : | 12/08 2004 | Written : | 11/05 2004 |
| Placement : | 5-7 semester | Hours per week : | 4 |
| Length : | 1 semester | Teaching Language : | Danish if no English students are present |
| Objective : | ANN provides the student with knowledge about Artificial Neural Network i.e. the principles of neural network, learning algorithms, testing and usage. Gain experience designing neural networks. Enable the student to understand advanced neural network technology in order to continue studying the literature within the field. |
||
| Principal Content : | Introduction to the principles of the human brain, neurons, dendrites, axom,…. Artificial Neural Network components: - Adaline, perceptron, multiplayer perceptrons - Linear models, estimation, regression, least square, LMS algorithm - Patterns recognition, classifiers, training parameters’ - Training algoritms, backpropagation,adaptive systems - Nonlinear models, perceptron, MLP, training, classification, error and stopcriterias - Function approximation with MLP, Radial Basis funcionc, vector support machines - Hebbian learning, Oja´s rule, anti-hebbian learning, Associate memory, winner-take-all network, adaptive resonance theory - Digital signal processing, time series, frequency domain, adaptive filters - Static versus Dynamic systems, time-delay neural network, gamma memory - Training and using recurrent network, feedback parameters, hopfield network, Grossbergs additive model - Introduction to pulsed neural network and related electronics |
||
| Teaching method : | The curriculum is based on an interactive book – overview lessons will allow (groups of) the student to study the interactive sessions and perform the related simulation exercises. | ||
| Required prequisites : | Documented knowledge of math corresponding to DSM3/DSM4 Analogue or digital design equivalent to 4th semester level. |
||
| Recommended prerequisites : | Knowledge of statistics is a benefit | ||
| Relations : | The principles of neural networks are used in many other fields like Control-theory, Image-technique, Noise reduction, Robot-control, Sonar-analysis, Radar tracking systems, Planning, Microwave simulation. | ||
| Type of examination : | Look under remarks | ||
| External examiner : | Internal | ||
| Marking : | Passed/Not passed | ||
| Remarks : | Examination: To pass the course the students must be present at min. 80% of the lessons and each student must hand in reports on 2 mandatory practical sessions, which must be accepted. |
||
| Teaching material : | Neural and Adaptive Systems, Fundamental through simulations by Jose C. Principe, Neil R. Euliano, W. Curt Lefebvre, ISBN 0-471-35167-9 from 1999 (A cd containing the electronics version of the book is included with the book together with version 3 of the simulation tool Neurosolutions). Supplementary Literature: Psychology, Themes and Variations by Wayne Weiten, ISBN 0-534-36714-3 (chapter 3 describes the biological bases of behavior) Neuroscience, Exploring the Brain by Mark F. Bear, B.W: Connors, M.A. Paradiso. ISBN 0-683-30596-4. Neural Network, a comprehensive foundation by Simon Haykin. ISBN 0-13-908385-5. Neural Networks for RF and Micorwave design by O.J. Zhang, K.C. Gupta. ISBN 0-58053-100-8. Theoretical Neuroscience, Computational and Mathematical Modeling of Neural Systems by Peter Dayan and L.F. Abbot. ISBN 0-262-04199-5. Pulsed Neural Networks by Maass and Bishop, editors. ISBN 0-262-13350-4. Handbook of Neural Networks for speech processing by Shigeru Katagiri. ISBN 0-89006-954-9. |
||
| Responsible teacher : | Kurt Jeritslev
, kuj@ihk.dk |
||