1.

Record Nr.

NYU004625618

Autore

[Sher, Gene I.]

Titolo

Handbook of neuroevolution through Erlang / Gene I. Sher

Pubbl/distr/stampa

New York, NY : Springer, ©2013

ISBN

9781461444633

1461444632

1461444624

9781461444626

Descrizione fisica

1 online resource

Classificazione

54.10

54.72

Disciplina

570.285

Collocazione

Electronic access

Lingua di pubblicazione

Inglese

Formato

Materiale a stampa

Livello bibliografico

Monografia

Nota di bibliografia

Includes bibliographical references.

Nota di contenuto

Part 1. FOUNDATIONS -- Introduction to Neural Networks -- Introduction to Evolutionary Computation -- Introduction to Neuroevolutionary Methods -- The Unintentional Neural Network Programming Language -- Introduction: Applications & Motivations -- Part 2. NEUROEVOLUTION: TAKING THE FIRST STEP -- Developing a Feed Forward Neural Network -- Adding the "Stochastic Hill-Climber" Learning Algorithm -- Developing a Simple Neuroevolutionary Platform -- Testing the Neuroevolutionary System -- Part 3. A Case Study -- DXNN: A Case Study -- Part 4. Advanced Neuroevolution: Creating the Cutting Edge -- 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 -- Part 5. Applications -- Artificial Life -- Evolving Currency Trading Agents -- Part 6. Promises Kept -- Conclusion.

Sommario/riassunto

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.