From Synapses to Rules: Discovering Symbolic Rules from Neural Processed Data Book

I	The Theoretical Bases of Learning	1
1	The Statistical Bases on Learning	5
2	PAC Meditation on Boolean Formulas	41
3	Learning Regression Functions	61
4	Cooperative Games in a Stochastic Environment	75
5	If-Then-Else and Rule Extraction from Two Sets of Rules	87
6	Extracting Interpretable Fuzzy Knowledge from Data	109
7	Fuzzy Methods for Simplifying a Boolean Formula Inferred from Examples	117
II	Physical Aspects of Learning	135
8	On Mapping and Maps in the Central Nervous System	139
9	Molecular Basis of Learning and Memory: Modelling Based on Receptor Mosaics	165
10	Physiological and Logical Brain Functionalities: A Hypothesis for a Self-Referential Brain Activity	197
11	Modeling of Spontaneous Bursting Activity Observed in In-Vitro Neural Networks	219
12	The Importance of Data for Training Intelligent Devices	229
13	Learning and Checking Confidence Regions for the Hazard Function of Biomedical Data	251
III	Systems that Bridge the Gap	273
14	Integrating Symbol-Oriented and Sub-Symbolic Reasoning Methods into Hybrid Systems	275
15	From the Unconscious to the Conscious	293
16	On Neural Networks, Connectionism and Brain-Like Learning	315
17	Adaptive Computation in Data Structures and Webs	343
18	IUANT: An Updating Method for Supervised Neural Structures	363
	Conclusions	371
	References	372
	Index	385