- We will send in 10–14 business days.
/images/books/3637875/9780521445320.jpg)
- Author: Jean-Pierre Aubin
- Publisher: Cambridge University Press
- ISBN-10: 0521445329
- ISBN-13: 9780521445320
- Format: 15.5 x 23.1 x 2 cm, kieti viršeliai
- Language: English
- SAVE -10% with code: EXTRA
Reviews
Description
This book is devoted to some mathematical methods that arise in two domains of artificial intelligence: neural networks and qualitative physics. Professor Aubin makes use of control and viability theory in neural networks and cognitive systems, regarded as dynamical systems controlled by synaptic matrices, and set-valued analysis that plays a natural and crucial role in qualitative analysis and simulation. This allows many examples of neural networks to be presented in a unified way. In addition, several results on the control of linear and nonlinear systems are used to obtain a "learning algorithm" of pattern classification problems, such as the back-propagation formula, as well as learning algorithms of feedback regulation laws of solutions to control systems subject to state constraints.
EXTRA 10 % discount with code: EXTRA
The promotion ends in 23d.20:59:29
The discount code is valid when purchasing from 10 €. Discounts do not stack.
- Author: Jean-Pierre Aubin
- Publisher: Cambridge University Press
- ISBN-10: 0521445329
- ISBN-13: 9780521445320
- Format: 15.5 x 23.1 x 2 cm, kieti viršeliai
- Language: English English
This book is devoted to some mathematical methods that arise in two domains of artificial intelligence: neural networks and qualitative physics. Professor Aubin makes use of control and viability theory in neural networks and cognitive systems, regarded as dynamical systems controlled by synaptic matrices, and set-valued analysis that plays a natural and crucial role in qualitative analysis and simulation. This allows many examples of neural networks to be presented in a unified way. In addition, several results on the control of linear and nonlinear systems are used to obtain a "learning algorithm" of pattern classification problems, such as the back-propagation formula, as well as learning algorithms of feedback regulation laws of solutions to control systems subject to state constraints.
Reviews