Learning Systems - Aved'yan, Eduard
69,99 €
versandkostenfrei*

inkl. MwSt.
Versandfertig in 2-4 Wochen
35 °P sammeln
  • Broschiertes Buch

A learning system can be defined as a system which can adapt its behaviour to become more effective at a particular task or set of tasks. It consists of an architecture with a set of variable parameters and an algorithm. Learning systems are useful in many fields, one of the major areas being in control and system identification. This work covers major aspects of learning systems: system architecture, choice of performance index and methods measuring error. Major learning algorithms are explained, including proofs of convergence. Artificial neural networks, which are an important class of…mehr

Produktbeschreibung
A learning system can be defined as a system which can adapt its behaviour to become more effective at a particular task or set of tasks. It consists of an architecture with a set of variable parameters and an algorithm. Learning systems are useful in many fields, one of the major areas being in control and system identification. This work covers major aspects of learning systems: system architecture, choice of performance index and methods measuring error. Major learning algorithms are explained, including proofs of convergence. Artificial neural networks, which are an important class of learning systems and have been subject to rapidly increasing popularity, are discussed. Where appropriate, examples have been given to demonstrate the practical use of techniques developed in the text. System identification and control using multi-layer networks and CMAC (Cerebellar Model Articulation Controller) are also presented.
  • Produktdetails
  • Verlag: Springer / Springer, Berlin
  • Artikelnr. des Verlages: 978-3-540-19996-0
  • 1st Edition.
  • Seitenzahl: 136
  • Erscheinungstermin: 25. Oktober 1995
  • Englisch
  • Abmessung: 235mm x 155mm x 7mm
  • Gewicht: 230g
  • ISBN-13: 9783540199960
  • ISBN-10: 3540199969
  • Artikelnr.: 26674768
Inhaltsangabe
1 Introduction to Learning Systems.- 1.1 Systems, Memory.- 1.2 Performance Index.- 1.2.1 Random Input.- 1.2.2 Deterministic Input.- 1.3 Learning Algorithms.- 1.4 Some Examples of Learning Systems.- 1.4.1 The Learning Linear Combiner.- 1.4.2 Neurons of Higher Order.- 1.4.3 The Learning Non-Linear Transformer.- 1.4.4 Linear and Non-Linear Learning Filters.- 1.4.5 Learning control systems.- 1.4.6 The Learning Multilayer Neural Network.- 1.4.7 Learning CMAC.- References.- 2 Deterministic Algorithms.- 2.1 Simple Projection Algorithms in Spaces With Different Norms (Structure, Convergence, Properties).- 2.1.1 Construction Of Kaczmarz Algorithm.- 2.1.2 Convergence.- 2.2 Modified Projection Algorithms With a High Rate of Convergence.- 2.2.1 Construction.- 2.2.2 Transient Mode.- 2.2.3 Properties Of The Estimates.- 2.2.4 "Bad" Measurements.- References.- 3 Deterministic and Stochastic Algorithms of Optimisation.- 3.1 Deterministic Methods for Unconstrained Minimisation.- 3.1.1 The Gradient