Gerasimos G. Rigatos

Advanced Models of Neural Networks (eBook, PDF)

Nonlinear Dynamics and Stochasticity in Biological Neurons

• Format: PDF

Produktbeschreibung

Suitable for researchers engaged with neural networks and dynamical systems theory

Introduces advanced models of neural networks

Includes several chapters suitable for related postgraduate courses in engineering, computer science, mathematics, physics and biology

---

Dieser Download kann aus rechtlichen Gründen nur mit Rechnungsadresse in A, B, BG, CY, CZ, D, DK, EW, E, FIN, F, GR, HR, H, IRL, I, LT, L, LR, M, NL, PL, P, R, S, SLO, SK ausgeliefert werden.

Produktdetails

• Verlag: Springer Berlin Heidelberg
• Seitenzahl: 275
• Erscheinungstermin: 27. August 2014
• Englisch
• ISBN-13: 9783662437643
• Artikelnr.: 43792016

Autorenporträt

Dr. Gerasimos Rigatos received his Ph.D. from the Dept. of Electrical and Computer Engineering of the National Technical University of Athens, Greece. He had a postdoctoral position at IRISA, Rennes, France, he was an invited professor at the Université Paris XI (Institut d'Eléctronique Fondamentale) and a lecturer in the Dept. of Engineering of Harper-Adams University College, UK. He is now a researcher in the Unit of Industrial Automation, Industrial Systems Institute, Patras, Greece. His research interests include computational intelligence, adaptive systems, mechatronics, robotics and control, optimization and fault diagnosis.

Inhaltsangabe

Modelling Biological Neurons in Terms of Electrical Circuits.- Systems Theory for the Analysis of Biological Neuron Dynamics.- Bifurcations and Limit Cycles in Models of Biological Systems.- Oscillatory Dynamics in Biological Neurons.- Synchronization of Circadian Neurons and Protein Synthesis Control.- Wave Dynamics in the Transmission of Neural Signals.- Stochastic Models of Biological Neuron Dynamics.- Synchronization of Stochastic Neural Oscillators Using Lyapunov Methods.- Synchronization of Chaotic and Stochastic Neurons Using Differential Flatness Theory.- Attractors in Associative Memories with Stochastic Weights.- Spectral Analysis of Neural Models with Stochastic Weights.- Neural Networks Based on the Eigenstates of the Quantum Harmonic Oscillator.- Quantum Control and Manipulation of Systems and Processes at Molecular Scale.- References.- Index.

Rezensionen

"Several chapters deal with standard questions like control, synchronization, and estimation. Rigatos uses a clever linearization technique, and then applies variants of linear control techniques to solve these problems for nonlinear models. ... I recommend this book to those interested in neural nets who won't be put off by the density of the mathematics." (Paul Cull, Computing Reviews, December, 2014)