Automated Knowledge Acquisition
This tutorial provides clear explanations of techniques for automated knowledge acquisition. Covers topics such as induction algorithms using decision trees; induction algorithms using progressive rule generation; sub-symbolic learning methods, artificial neural networks; other machine learning paradigms; theoretical considerations; the extraction of rules and concepts using a single-layered Hebbian neural network; BRAINNE - automated knowledge acquisition using multi-layered neural network; and BRAINNE in the real world. For computer professionals who wish to gain a good understanding of automated knowledge acquisition techniques.
22 pages matching inhibitory in this book
Results 1-3 of 22
What people are saying - Write a review
We haven't found any reviews in the usual places.
Induction algorithms using decision trees
Induction algorithms using progressive
Subsymbolic learning methods artificial neural
9 other sections not shown
antecedent Artificial Intelligence associated automated knowledge acquisition Back-propagation BIRD BRAINNE Chapter Chi-square classified clusters cognitive Color conceptual model conjunctive rule connectionism connectionist connectionist expert systems considered contributory inputs criterion decision tree Delta Rule determined digit Dillon disjunctive rules DOLPHIN domain Down-center Down-left Down-right Egglaying AND Fly EURISKO expert systems extracted Feathers AND Egglaying FIELD-B Fly-short-d genetic algorithms given Gray Hair AND Milk heuristics hidden units human induction inhibitory initial input attributes instance knowledge representation Kohonen learning algorithm Lenat machine learning MAMMAL MARSUPIAL Michalski Mid-center Milk AND Placenta Morgan Kaufmann multi-layered neural network negative example neuron number of examples output layer output nodes output unit Parallel Distributed Processing Placenta positive examples problem production rules real-world represent rule defining Rumelhart Rumelhart 1988 selectors Shavlik shown in Figure string structure sub-symbolic subset Swims symbolic Table Touretzky training set unsupervised learning Up-center Up-left Up-right values zero