Knowledge Acquisition and Machine Learning: Theory, Methods, and Applications Book

1	The Knowledge Acquisition Framework	1
1.1	The Knowledge Acquisition Problem	1
1.2	Domain Modeling for Expert Systems	2
1.3	Machine Learning	17
1.4	A Characterization of MOBAL	24
2	The Knowledge Representation Environment	27
2.1	Mobal's knowledge representation	28
2.2	Formal Properties	36
2.3	The Human-Computer Interface	60
2.4	The Programmer's Interface	66
3	The Inference Engine IM-2	69
3.2	The Knowledge Representation in IM-2	73
3.3	The Inference Mechanism	96
3.4	Reason Maintenance	101
4	The Sort Taxonomy	109
4.2	The Sort Lattice	117
4.3	Computing the Sort Lattice	129
4.4	The Many Sorted Logic	138
4.5	The Sort Taxonomy Tool	145
5	The Predicate Structure	149
5.1	The Tasks of the PST	149
5.2	PST: Representation and Operations	151
5.3	The Automatic Generation of a Topology	155
5.4	Topology-influenced Learning	161
5.5	Results	164
6	Model-driven Rule Discovery	169
6.2	The Learning Task of RDT	170
6.3	Other Approaches to Hypothesis Space Reduction	171
6.4	Model-driven Learning	173
6.5	Model Knowledge in RDT	174
6.6	The RDT Algorithm	178
6.7	Future Research and Summary	190
7	Knowledge Revision	193
7.1	The Maintenance Problem	193
7.2	An Overview of KRT	195
7.3	Minimal Base Revisions	198
7.4	Choosing Preferred Revisions	206
7.5	Confidence Propagation	207
7.6	Plausibility and Non-minimal Revisions	209
7.7	Support Set Reformulation	210
7.8	Example	210
7.9	Properties of the Reformulation Operators	215
7.10	Search Strategy	217
7.11	Related Work	218
8	Concept Formation	221
8.1	Representation Bias in Learning	221
8.2	Constructive Induction vs. Concept Formation	223
8.3	The Representation of Concepts in Mobal	226
8.4	Demand-driven Concept Formation	229
8.5	Evaluating CLT	236
8.6	Related Work	241
9	Practical Experiences	245
9.1	The Traffic-law Domain	248
9.2	The Icterus Domain	256
9.3	The Telecommunications Security Domain	275
	Bibliography	281
	Author Index	295
	Name Index	299
	Subject Index	301