Synopses & Reviews
The book aims to propose a theoretical and applicatory framework for extracting formal rules from data. To this end recent approaches in relevant disciplines are examined that bring together two typical goals of conventional Artificial Intelligence and connectionism - respectively, deducing within an axiomatic shell formal rules about a phenomenon and inferring the actual behavior of it from examples - into a challenging inferential framework where we learn from data and understand what we have learned. The goal is to obtain a translation of the subsymbolic structure of the data - stored in the synapses of a neural network - into formal properties described by rules.
To capture this journey from synapses to rules and then render it manageable for real world learning tasks, the contributions deal in depth with the following aspects: i. theoretical foundations of learning algorithms and soft computing; ii. intimate relationships between symbolic and subsymbolic reasoning methods; iii. integration of the related hosting architectures in both physiological and artificial brain.
Synopsis
The book aims to propose a theoretical and applicatory framework for extracting formal rules from data. To this end recent approaches in relevant disciplines are examined that bring together two typical goals of conventional Artificial Intelligence and connectionism - respectively, deducing within an axiomatic shell formal rules about a phenomenon and inferring the actual behavior of it from examples - into a challenging inferential framework where we learn from data and understand what we have learned. The goal is to obtain a translation of the subsymbolic structure of the data - stored in the synapses of a neural network - into formal properties described by rules. To capture this journey from synapses to rules and then render it manageable for real world learning tasks, the contributions deal in depth with the following aspects: i. theoretical foundations of learning algorithms and soft computing; ii. intimate relationships between symbolic and subsymbolic reasoning methods; iii. integration of the related hosting architectures in both physiological and artificial brain.
Table of Contents
I: The Theoretical Bases Of Learning. 1. The Statistical Bases Of Learning; B. Apolloni, S. Bassis, S. Gaito, D. Malchiodi. 2. Pac Meditation On Boolean Formulas; B. Apolloni, S. Baraghini, G. Palmas. 3. Learning Regression Functions; B. Apolloni, S. Gaito, D. Iannizzi, D. Malchiodi. 4. Cooperative Games In A Stochastic Environment; B. Apolloni, S. Bassis, S. Gaito, D. Malchiodi. 5. If-Then-Else And Rule Extraction From Two Sets Of Rules; D. Mundici. 6. Extracting Interpretable Fuzzy Knowledge From Data; C. Mencar. 7. Fuzzy Methods For Simplifying A Boolean Formula Inferred From Examples; B. Apolloni, D. Malchiodi, C. Orovas, A.M. Zanaboni. II: Physical Aspects Of Learning. 8. On Mapping And Maps In The Central Nervous System; G.E.M. Biella. 9. Molecular Basis Of Learning And Memory: Modelling Based On Receptor Mosaics; L.F. Agnati, L.M. Santarossa, F. Benfenati, M. Ferri, A. Morpurgo, B. Apolloni, K. Fuxe. 10. Physiological And Logical Brain Functionalities: A Hypothesis For A Self-Referential Brain Activity; B. Apolloni, A. Morpurgo, L.F. Agnati. 11. Modeling Of Spontaneous Bursting Activity Observed In In-Vitro Neural Networks; M. Marinaro, S. Scarpetta. 12. The Importance Of Data For Training Intelligent Devices; A. Esposito. 13. Learning And Checking Confidence Regions For The Hazard Function Of Biomedical Data; B. Apolloni, S. Gaito, D. Malchiodi. III: Systems That Bridge The Gap. 14. Integrating Symbol-Oriented And Sub-Symbolic Reasoning Methods Into Hybrid Systems; F.J. Kurfess. 15. From The Unconscious To The Conscious; Ron Sun. 16. On Neural Networks, Connectionism And Brain-Like Learning; A. Roy. 17. Adaptive Computation In Data Structures And Webs; M. Gori. 18. Iuant: An Updating Method For Supervised Neural Structures; S. Gentili. Index.