Neural-Symbolic Learning Systems: Foundations and Applications
Springer Science & Business Media, Aug 6, 2002 - Computers - 271 pages
Artificial Intelligence is concerned with producing devices that help or replace human beings in their daily activities. Neural-symbolic learning systems play a central role in this task by combining, and trying to benefit from, the advantages of both the neural and symbolic paradigms of artificial intelligence.
This book provides a comprehensive introduction to the field of neural-symbolic learning systems, and an invaluable overview of the latest research issues in this area. It is divided into three sections, covering the main topics of neural-symbolic integration - theoretical advances in knowledge representation and learning, knowledge extraction from trained neural networks, and inconsistency handling in neural-symbolic systems. Each section provides a balance of theory and practice, giving the results of applications using real-world problems in areas such as DNA sequence analysis, power systems fault diagnosis, and software requirements specifications.
Neural-Symbolic Learning Systems will be invaluable reading for researchers and graduate students in Engineering, Computing Science, Artificial Intelligence, Machine Learning and Neurocomputing. It will also be of interest to Intelligent Systems practitioners and anyone interested in applications of hybrid artificial intelligence systems.
What people are saying - Write a review
Other editions - View all
4min activate x activation function activation values Alarm auxiliary Alarm breaker.open Amin answer set applied artificial neural networks assume background knowledge Backpropagation Belief Revision bypass C-IL2P networks Chapter clause computes Connectionist connections cruise control database define Definition derive Diamond problem disjunctive DNA sequence encoded Equation extract rules extraction algorithm fault diagnosis fixpoint hidden neuron Hidden to Output inconsistencies inductive learning input layer input neurons input vectors KBANN Knowledge Extraction learning algorithm Light-On line0l machine learning minimal learning negative weights network of Figure neural networks nonmonotonic obtained output layer output neuron override performance positive form problem Proposition Pruning Rule represent result rule extraction rule set satisfied semi-linear set of input set of rules simplification single hidden layer splice junction stable model subnetworks subset sup(I SwitchA-On Theorem threshold toofast trained network training examples transformer02 Translation Algorithm Truth Maintenance Systems Wxrk