Handbook of Neuroevolution Through Erlang

Gene I. Sher (Autor)

Buch | Hardcover

831 Seiten

2012 | 2013 ed.
Springer-Verlag New York Inc.
978-1-4614-4462-6 (ISBN)

Artikel merken

Handbook of Neuroevolution Through Erlang presents both the theory behind, and the methodology of, developing a neuroevolutionary-based computational intelligence system using Erlang. With a foreword written by Joe Armstrong, this handbook offers an extensive tutorial for creating a state of the art Topology and Weight Evolving Artificial Neural Network (TWEANN) platform. In a step-by-step format, the reader is guided from a single simulated neuron to a complete system. By following these steps, the reader will be able to use novel technology to build a TWEANN system, which can be applied to Artificial Life simulation, and Forex trading. Because of Erlang’s architecture, it perfectly matches that of evolutionary and neurocomptational systems. As a programming language, it is a concurrent, message passing paradigm which allows the developers to make full use of the multi-core & multi-cpu systems. Handbook of Neuroevolution Through Erlang explains how to leverage Erlang’s features in the field of machine learning, and the system’s real world applications, ranging from algorithmic financial trading to artificial life and robotics.

Introduction: Applications & Motivations.- Introduction to Neural Networks.- Introduction to Evolutionary Computation.- Introduction to Neuroevolutionary Methods.- The Unintentional Neural Network Programming Language.- Developing a Feed Forward Neural Network.- Adding the “Stochastic Hill-Climber” Learning Algorithm.- Developing a Simple Neuroevolutionary Platform.- Testing the Neuroevolutionary System.- DXNN: A Case Study.- Decoupling & Modularizing Our Neuroevolutionary Platform.- Keeping Track of Important Population and Evolutionary Stats.- The Benchmarker.- Creating the Two Slightly More Complex Benchmarks.- Neural Plasticity.- Substrate Encoding.- Substrate Plasticity.- Artificial Life.- Evolving Currency Trading Agents.- Conclusion.

Erscheint lt. Verlag	6.11.2012
Zusatzinfo	172 Illustrations, black and white; XX, 831 p. 172 illus.
Verlagsort	New York, NY
Sprache	englisch
Maße	155 x 235 mm
Themenwelt	Informatik ► Software Entwicklung ► Objektorientierung
	Informatik ► Theorie / Studium ► Künstliche Intelligenz / Robotik
	Informatik ► Weitere Themen ► Bioinformatik
	Naturwissenschaften ► Biologie
Schlagworte	Artificial Life
ISBN-10	1-4614-4462-4 / 1461444624
ISBN-13	978-1-4614-4462-6 / 9781461444626
Zustand	Neuware