541-0888/01 – Expert Systems in GIS (ES_GIS_D)
| Gurantor department | Department of Geological Engineering | Credits | 0 |
| Subject guarantor | doc. RNDr. František Staněk, Ph.D. | Subject version guarantor | doc. RNDr. František Staněk, Ph.D. |
| Study level | postgraduate | Requirement | Optional |
| Year | | Semester | winter + summer |
| | Study language | Czech |
| Year of introduction | 2001/2002 | Year of cancellation | 2010/2011 |
| Intended for the faculties | HGF | Intended for study types | Doctoral |
Subject aims expressed by acquired skills and competences
The first part of this course is dedicated to solving expert problems. These problems can arise from other courses as well as from practice. The main emphasis lays in explanation of fundamental principles of problem solving strategies and of their general properties. The students learn how to decide which procedure is a suitable tool for solving a specific problem. An important ingredient of the course is algorithmic implementation in PROLOG language. The students learn how to use existing Expert Systems, too.
The second part of the course deals with basic types of Artificial Neural Networks and with the way in which to understand these networks from both theoretical and practical points of view. The students are taught how to use these general methods to solve the problems arising from other courses of their study and from practice.
Teaching methods
Lectures
Individual consultations
Project work
Summary
Introduction to Artificial Intelligence (AI). Languages of AI. Introduction to PROLOG. Problem solving strategies. Expert System (ES). Describe the characteristics, features, structures, limitations, and benefits of ES. Describe the various methods of knowledge representation and build simple rule-based knowledge bases. Describe the various methods of inference. Conduct manual backward and forward chaining inferences. Artificial Neural Networks. The most common models like Backpropagation multilayered, Recurrent multilayered, Kohonen, Counterpropagation, Hopfield, BAM and ART nets are introduced. Object-oriented model of all mentioned types of neural networks. Expert System and Neural Network. Applications of Neural Network in Imaging Processing.
Compulsory literature:
Giarratano, J., Riley, G.: Expert Systems: Principles and Programming. 4th ed. Boston: Thomson Course Technology, 2005, 842 s.
Recommended literature:
Nilsson, N.J.: Artificial Intelligence: A New Synthesis. Morgan Kaufmann, 1998
Additional study materials
Way of continuous check of knowledge in the course of semester
E-learning
Other requirements
Prerequisities
Subject has no prerequisities.
Co-requisities
Subject has no co-requisities.
Subject syllabus:
Jazyky umělé inteligence. Metody hledání řešení. Charakteristika, vlastnosti a
architektura expertních systémů. Reprezentace znalostí. Pravidla a inferenční
sítě. Řídící mechanismy. Neuronové sítě. Modely neuronů. Vícevrstvé topologie.
Metody Backpropagation. Parametrická Backpropagation. Implementace neuronů s
intervalovým stavem excitace. Zobecnělá metoda Backpropagation pro neuronové
sítě s neurčitostí. Rekurentní vícevrstvé neuronové sítě. Kohonenovo učení a
samoorganizující se neuronové sítě. LVQ modely a counter-propagation
Hopfieldovy sítě. Boltzmannův stroj. Dvousměrná asociativní paměť. Adaptivní
rezonanční teorie. Objektově-orientovaný přístup k modelování neuronových sítí.
Expertní systémy využívající neurovné sítě. Neuronové zpracování obrazové
informace.
Conditions for subject completion
Occurrence in study plans
Occurrence in special blocks
Assessment of instruction
Předmět neobsahuje žádné hodnocení.