Research Catalog

Title

Neural nets : a theory for brains and machines / A.F. Rocha.

Author

Rocha, A. F. (Armando Freitas), 1946-

Publication

Berlin ; New York : Springer-Verlag, ©1992.

Items in the Library & Off-site

Details

Description

xv, 393 pages : illustrations; 25 cm.

Summary

"The purpose of this book is to develop neural nets as a strong theory for both brains and machines. The theory is developed in close correlation with the biology of the neuron and the properties of human reasoning. This approach implies the following: - Updating the biology of the artificialneuron. The neurosciences have experienced a tremendous development in the last 50 years. One of the main purposes of the present work is toincorporate this knowledge into a strong model of the artificial neuron. Particular attention is devoted to formalizing the complex chemical processes at the synaptic level. This formal language supports both symbolicreasoning and uncertainty processing. - Investigating the properties of expert reasoning. This kind of reasoning is approximate, partial and non-monotonic, and therefore requires special mathematical tools for its formalization, such as fuzzy set theory and fuzzy logic. Three different intelligent systems developed with this technology are presented and discussed."--PUBLISHER'S WEBSITE.

Series Statement

Lecture notes in computer science ; 638. Lecture notes in artificial intelligence

Uniform Title

• Lecture notes in computer science ; 638.
• Lecture notes in computer science. Lecture notes in artificial intelligence

Subject

• Neural networks (Computer science)
• Brain > Physiology
• Neural circuitry
• Models, Neurological
• Nerve Net
• Neural Networks, Computer
• Neural Pathways > physiology
• Neural circuitry
• Brain > Physiology
• Künstliche Intelligenz
• Neuronales Netz
• Neurale netwerken
• Artificial intelligence
• Réseaux neuronaux (physiologie)

Bibliography (note)

• Includes bibliographical references and index.

Contents

• Ch. I. The Neuron -- 1. Composition and properties of the cellular membrane -- 2. The Hodgkin-Huxley model -- 3. The neural encoding -- 4. Measuring the entropy of the neural code -- 5. The plastic axonic encoding -- 6. Controlling the axonic encoding -- 7. The sensory world -- Ch. II. The Synapsis: Electrical Properties -- 1. Structure and physiology -- 2. Electrophysiology -- 3. The early stages of the electrical processing -- 4. The axonic processing -- 5. Controlling the energy available to the membrane -- 6. The neuron as a multipurpose processor -- a. The neuron as a numeric processor -- b. The neuron as a sequential processor -- c. The MAPI structure supports fuzzy logic -- d. The MAPI structure supports mathematical programming -- 7. The formal neuron -- 8. Fuzzy logic control: an example -- Ch. III. The Synapsis: The Chemical Processing -- 1. The production of proteins -- 2. Specifying transmitters and post-synaptic receptors -- 3. The plasticity of the chemical encoding -- 4. Modulator learning control -- 5. A formal genetic code -- 6. An example of formal genetic encoding -- 7. A formal chemical language -- 8. Updating the formal neuron -- 9. Growing up a neural net -- 10. The algorithmic chemical processing -- 11. Combining numeric and symbolic processing in a MPNN -- 12. Mail and broadcasting -- 13. Consequences and future research -- Ch. IV. Learning -- 1. Modeling -- 2. The evolutive reasoning machine -- 3. Evolutive learning
• 4. Inductive learning -- 5. The role of memory -- 6. The labelling of MPNNs -- 7. Other properties of the inductive [sigma]-models -- 8. Inductive and deductive learning -- 9. Evolution of learning -- 10. Creativity -- 11. An example for use of ERM -- 12. Some related theories -- Ch. V. Investigating Expertise -- 1. The purpose -- 2. Knowledge elicitation: The jargon list, knowledge graph, and relevance -- 3. The "mean" knowledge: Graph summation, relevance and labels, fuzzy indexes, and averaging -- 4. Aggregation at the non-terminal nodes -- 5. Types of non-terminal nodes -- 6. Declarative knowledge: Gain of confidence, support and refutation -- 7. Procedural knowledge: Cost and benefit -- 8. Decision making in therapy -- 9. Non-monotonic reasoning: Default reasoning -- 10. The uncertainty state space -- 11. MPNN supports expertise -- 12. Properties of the expert reasoning -- Ch. VI. Modular Nets -- 1. Modularity of knowledge -- 2. Modularity of the cortex -- 3. Modular MPNN -- 4. The library [actual symbol not reproducible] of neurons -- 5. Basic circuits -- 6. Specifying the structure of the modules -- 7. The computational structure of MPNN -- 8. MPNN hierarchy: Afferent nets, efferent nets -- 9. The learning control. 10. Conclusion -- Ch. VII. NEXTOOL: A MPNN Classifying System -- 1. Some initial words about classification -- 2. The general structure of NEXTOOL -- 3. The expert knowledge net -- 4. The semantic net
• 5. Writing the ESN into the MPNNs of the EKN -- 6. Using MPNNs to encode SNs -- 7. The inductive learning rules of NEXTOOL -- 8. Deductive learning -- 9. The evolutive learning engine -- 10. Deciding about inductive and deductive learning -- 11. The inference machine -- 12. The interfaces with the external world -- 13. Learning from a medical data base. 14. Conclusion -- Ch. VIII. JARGON: A Neural Environment for Language Processing -- 1. Jargon: a specialized subset of natural language -- 2. Theme and rheme -- 3. Investigating speech understanding -- 4. The theoretical background supporting JARGON -- 5. The word net WN -- 6. The phrase net PN -- 7. Implementing the syntax -- 8. Learning the semantic by being told -- 9. Recodifying the NLDB -- 10. The text net TN -- 11. Handling the leprosy data dase -- 12. JARGON's multifunctions -- Ch. IX. SMART KARDS(c): Object Oriented MPNN Environment -- 1. MPNN systems and object oriented programming -- 2. Introducing SMART KARDS(c) -- a. Kardic -- b. Kardplan -- c. Kardtex -- d. Self-referred system -- 3. The expert environment -- 4. Leprosy: an example of application -- 5. The patients -- 6. The experts -- 7. Reasoning with the expert knowledge -- 8. Reasoning with standard patterns -- 9. The outpatient service -- 10. Programming actions -- 11. Implementing routines -- 12. Learning indices -- 13. Learning forms -- 14. An intelligent MPNN environment -- Ch. X. Fuzzy Sets and Fuzzy Logic
• 1. Introduction -- 2. Fuzzy Sets -- 3. [actual symbol not reproducible] -norms and [actual symbol not reproducible] -- conorms -- 4. Fuzzy variables and possibility theory -- 5. Linguistic variables -- 6. Linguistic quantifiers -- 7. Fuzzy Logic.

ISBN

• 3540559493
• 9783540559498
• 0387559493
• 9780387559490

LCCN

92031542

OCLC

• ocm26396091
• 26396091
• SCSB-1965226

Owning Institutions

Princeton University Library