Title Details: | |
Fuzzy and neurofuzzy systems – Fuzzy Deep Learning |
|
Authors: |
Mastorocostas, Paris |
Subject: | HUMANITIES AND ARTS > LOGIC AND PHILOSOPHY OF LOGIC > LOGICS > NONCLASSICAL LOGICS > FUZZY LOGIC MATHEMATICS AND COMPUTER SCIENCE > COMPUTER SCIENCE > ALGORITHMS AND COMPLEXITY > ALGORITHMIC STRATEGIES MATHEMATICS AND COMPUTER SCIENCE > COMPUTER SCIENCE > COMPUTATIONAL SCIENCE > MODELING AND SIMULATION MATHEMATICS AND COMPUTER SCIENCE > COMPUTER SCIENCE > INTELLIGENT SYSTEMS MATHEMATICS AND COMPUTER SCIENCE > COMPUTER SCIENCE > INTELLIGENT SYSTEMS > ADVANCED MACHINE LEARNING MATHEMATICS AND COMPUTER SCIENCE > COMPUTER SCIENCE |
Keywords: |
Fuzzy systems
Fuzzy neural networks Recurrent models Fuzzy Deep Learning Fuzzy classifiers System identification Electric load forecasting Lung sounds separation Fuzzy clustering Scalable fuzzy rules Adaptive noise cancellation Fuzzy controllers |
Description: | |
Abstract: |
The book aims at familiarizing the reader (post graduate student in computer science or engineering) with significant areas of computational intelligence. Emphasis is put both on the theoretical mathematical background of fuzzy logic and design and training algorithms, as well as on a thorough description of main applications. In the first chapters the fundamentals of fuzzy logic are presented and the structure and operation of fuzzy rules and approximate reasoning are analyzed. The classical fuzzy system and its structure (fuzzifier, defuzzifier, rule base, inference engine) are studied. The design process of PIS, MIS, Takagi-Sugeno-Kang, fuzzy neural networks is given and the most prominent structure and parameter identification algorithms are examined, while genetic FRBCS are also described.
Recurrent fuzzy models and recurrent neural networks are introduced, along with dedicated learning techniques.
As far as real-world applications are concerned, the problems of sound processing, electric load forecasting, real-time separation of lung sounds and mining of telecommunications data are studied, while emphasis is also put on classification and automatic control.
The book concludes with the issue of fuzzy deep learning and a series of deep fuzzy structures is discussed.
Numerous models and algorithms have been implemented in MATLAB/Octave, such that the reader becomes familiar with scientific programming.
|
Linguistic Editors: |
Paxinou, Evgenia |
Graphic Editors: |
Tsakmaki, Eleni |
Type: |
Postgraduate textbook |
Creation Date: | 11-10-2022 |
Item Details: | |
ISBN |
978-618-5726-19-5 |
License: |
Attribution - NonCommercial - ShareAlike 4.0 International (CC BY-NC-SA 4.0) |
DOI | http://dx.doi.org/10.57713/kallipos-146 |
Handle | http://hdl.handle.net/11419/8672 |
Bibliographic Reference: | Mastorocostas, P. (2022). Fuzzy and neurofuzzy systems – Fuzzy Deep Learning [Postgraduate textbook]. Kallipos, Open Academic Editions. https://dx.doi.org/10.57713/kallipos-146 |
Language: |
Greek |
Consists of: |
1. Introduction to fuzzy logic – Fuzzy sets 2. Parameterized membership functions – Fuzzy relations 3. Fuzzy rules 4. Fuzzy approximate reasoning – Fuzzy rule bases 5. Fuzzy inference systems 6. Fuzzy models and fuzzy modelling 7. Fuzzy neural networks – TSK fuzzy systems 8. Fuzzy Systems with varying structure – Generalized fuzzy models 9. Recurrent fuzzy systems 10. Applications of recurrent fuzzy systems 11. Fuzzy controllers 12. Fuzzy rule-based classification systems 13. Deep learning fuzzy systems |
Number of pages |
382 |
Publication Origin: |
Kallipos, Open Academic Editions |
You can also view | |
User comments | |
There are no published comments available! | |