Artificial Neural Networks (IND 561) | GSÜ

Content

Objective

The aim of this course is to introduce artificial neural networks and discuss the basic ideas behind machine learning; present the concept of perceptron as a simple computing element and consider the perceptron learning rule; to introduce recurrent neural networks; explore Hebbian and competitive learning. Moreover, hybrid intelligent systems as a combination of different intelligent technologies will be introduced and evolutionary neural networks and fuzzy evolutionary systems will be discussed.

Course Content

1. week : Introduction to knowledge-base intelligent systems
2. week : Rule-based expert systems
3. week : Uncertainty management in rule-based expert systems
4. week : Fuzzy expert systems: Fuzzy logic
5. week : Frame-based expert systems
6. week : Artificial neural networks: Supervised learning
7. week : Artificial neural networks: Unsupervised learning
8. week : Evolutionary Computation: Genetic algorithms
9. week : Mid term
10. week : Evolutionary Computation: Evolution strategies and genetic programming
11. week : Hybrid intelligent systems: Neural expert systems and neuro-fuzzy systems
12. week : Hybrid intelligent systems: Evolutionary neural networks and fuzzy evolutionary systems
13. week : Knowledge engineering: Building neural network based systems
14. week : Data mining and knowledge discovery

Course Learning Outcomes

Upon successful completion of this course, students should be able to:
1. Define the principles behind intelligent systems.
2. Recognize what intelligent systems can and cannot do.
3. Enumerate typical applications of intelligent systems.
4. Explain which tools are most relevant for the task on-hand.
5. Explain how to use different artificial intelligence tools.
6. Explain how to build an intelligence system.
7. Design an artificial neural network.

Teaching and Learning Methods

Use of slideshow during the class and available online. Exercises applications during each class. Students propose seminar with reports and presentation.

References

Negnevitsky, M., Artificial Intelligence: A Guide to Intelligent Systems, Second Edition, Addison Wesley, 2004.

Weekly Contents

Theory Topics
Week	Weekly Contents
1	Introduction, Artificial Intelligence, Machine Learning
2	Linear Algebra Review
3	Linear regression with one variable and with multiple variables
4	Logistic regression with one variable and with multiple variables
5	Regularization
6	Neuron models and basic learning rules
7	Multi-layer perceptron
8	Midterm Examination
9	Different architectures
10	Associative memory and Hopfield Neural Network
11	Distance Based Neural Networks I
12	Distance Based Neural Networks II
13	Neural Network Trees
14	Clustering

Assessment System

Contribution to Overall Grade
Activities	Number	Contribution
Contribution of in-term studies to overall grade	1	60
Contribution of final exam to overall grade	1	40
Total	2	100

In-Term Studies
Activities	Number	Contribution
Assignments	4	15
Presentation	0	0
Midterm Examinations (including preparation)	1	25
Project	1	20
Laboratory	0	0
Other Applications	0	0
Quiz	0	0
Term Paper/ Project	0	0
Portfolio Study	0	0
Reports	0	0
Learning Diary	0	0
Thesis/ Project	0	0
Seminar	0	0
Other	0	0
Total	6	60

Relation of Proficiency

No	Program Learning Outcomes	Contribution
No	Program Learning Outcomes	1	2	3	4	5
1
2						X
3
4
5						X
6
7						X
8
9
10						X
11
12

ECTS

Activities	Number	Period	Total Workload
Class Hours	14	3	42
Working Hours out of Class	14	2	28
Assignments	4	5	20
Midterm Examinations (including preparation)	1	20	20
Project	1	20	20
Final Examinations (including preparation)	1	20	20
Total Workload			150
Total Workload / 25			6.00
Credits ECTS			6