EE 416T: ARTIFICIAL NEURAL NETWORKS
EEU 433: ARTIFICIAL NEURAL NETWORKS
&GENETIC ALGORITHM METHODS
S 7 Elective (D/G)
|L |T |P |C |
|3 |0 |0 |3 |
Objectives: To understand the principles of Artificial Neural Networks and Genetic Algorithms.
Level of the course: Understanding &Analysis Level
Prerequisite: NIL
MODULE 1 (11 hours)
Introduction to Artificial Neural Networks - Biological neurons .Computational models of neuron- McCulloch - Pitts model - types of activation function .Introduction to network architectures - knowledge representation - Learning process .Learning algorithms- - error-correction learning .Boltzmann learning-Hebbian learning, competitive learning- Learning paradigms- supervised learning - unsupervised learning - method of steepest descent - least mean square algorithms - adaline/medaline units . perceptrons- derivation of the back-propagation algorithm. Computer based simulation
MODULE 2 (11 hours)
Network architectures-MLFFN-RNN- RBF network structure - covers theorem and the separability of patterns - RBF learning strategies - comparison of RBF,RNN and MLP networks- Hopfield networks . associative memory-energy function - spurious states - error performance - simulated annealing - applications of neural networks . Forecasting-the XOR problem - traveling salesman problem - image compression using MLPs - character retrieval using Hopfield networks. Computer based simulation.
MODULE 3 (11 hours)
Genetic algorithm -Introduction to genetic algorithms . The genetic computation process-natural evolution-parent selection-crossover-mutation-properties - classification -
Application to engineering problems
MODULE 4 (9 hours)
Hybrid systems .limitations of ANN and GA.s-properties of concept of neuro-fuzzy and neuro-genetic systems- GA.s an optimization tool for ANN-Application of ANN in forecasting-Signal characterization-ECG Modeling-Fault diagnosis-Case Studies.
Reference books
1. Simon Haykin, Neural Network – A Comprehensive Foundation, 2nd Ed, Pearson Education, 2002.
2. Zurada J.M., Introduction to Artificial Neural Systems, Jaico Publishers,2003.
3. Bart Kosko, Neural Network and Fuzzy Systems, Prentice Hall of India, 2002
4. Goldberg D.E., .Genetic Algorithms in Search Optimization and Machine Learning, Addison Wesley,1989
5. Suran Goonatilake & Sukhdev Khebbal (Eds.), Intelligent Hybrid Systems., John Wiley,1995.
6. Hassoun Mohammed H, Fundamentals of Artificial Neural Networks, Prentice Hall of India, 2002.
................
................
In order to avoid copyright disputes, this page is only a partial summary.
To fulfill the demand for quickly locating and searching documents.
It is intelligent file search solution for home and business.
Related download
- tinge exchange rate model using a new neural network
- author guidelines for 8
- i model architecture jhu center for imaging science
- ee 416t artificial neural networks
- stock market prediction software using recurrent neural
- lecture notes in computer science
- final report plan template purdue university
- researchgate find and share research
Related searches
- neural networks for dummies
- artificial neural networks background
- neural networks ai
- neural networks from scratch pdf
- types of neural networks pdf
- graph neural networks ppt
- artificial neural networks pdf free
- neural networks and learning machines
- learning convolutional neural networks for graphs
- neural networks tutorial
- deep neural networks machine learning
- neural networks vs machine learning