Generalized Nets in Artificial Intelligence. Volume 6: Generalized Nets and Supervised Neural Networks

Generalized nets are a tool for modelling of parallel processes. They represent an extension of the concept of Petri nets and the rest of their modifications. In a series of books, generalized nets have been shown as a uniform language for description of various concepts and paradigms from the area of artificial intelligence. Artificial neural networks are a biologically inspired tool for modelling and optimization. They have a lot of modifications, depending on the pattern of connecting their components and the possibility of neural networks to learn over time. The present book contains our recent research aimed at describing in terms of generalized nets of the functioning and the results of the work of the class of neural networks that follow one of the major learning paradigms in artificial intelligence, that of the supervised learning.

Preface
Chapter 1. Short remarks on neural networks, index matrices and generalized nets

• Short remarks on neural networks
• Short remarks on index matrices
• Short remarks on generalized nets
• First generalized net model of neural network

Chapter 2. Generalized net models of supervised neural networks

• Modelling of the multilayer perceptron with a generalized net
• Modelling of the recurrent neural network with a generalized net
• Modelling of the Elman neural network with a generalized net
• Modelling of the time delay neural network with a generalized net
• Modelling of the distributed time delay neural network with a generalized net
• Modelling of the layered digital dynamic network with a generalized net
• Modelling the nonlinear autoregressive network with exogenous inputs with a generalized net
• Modelling the brain-state-in-a-box neural network with a generalized net
• Modelling the hierarchical neural network with a generalized net

Chapter 3. Modelling the backpropagation algorithms with generalized net models

• Modelling the algorithm backpropagation for learning of neural network with a generalized net. Part 1
• Modelling the algorithm backpropagation for learning of neural network with a generalized net. Part 2
• Modelling the accelerating backpropagation algorithm with generalized nets

Chapter 4. Modelling the optimization of neural networks with a generalized nets

• Generalized net model for parallel optimization of multilayer perceptron
• Generalized net model for parallel optimization of multilayer perceptron with variable learning rate backpropagation algorithm
• Generalized net model for parallel optimization of multilayer perceptron with variable learning rate backpropagation algorithm with time limit
• Generalized net model for parallel optimization of multilayer perceptron with momentum backpropagation algorithm
• Generalized net model for parallel optimization of multilayer perceptron with conjugate gradient backpropagation algorithm

Conclusion
References