The Art and Science of Machine Intelligence

1. Front Matter

   Pages i-xxii

   PDF

2. Background on Genetic Algorithms

   • Walker H. Land Jr., J. David Schaffer

   Pages 1-44

3. The Support Vector Machine

   • Walker H. Land Jr., J. David Schaffer

   Pages 45-76

4. The Generalized Regression Neural Network Oracle

   • Walker H. Land Jr., J. David Schaffer

   Pages 77-105

5. Alzheimer’s Disease and Speech Background

   • Walker H. Land Jr., J. David Schaffer

   Pages 107-135

6. Hybrid GA-SVM-Oracle Paradigm

   • Walker H. Land Jr., J. David Schaffer

   Pages 137-155

7. Classical Bayesian Theory and Networks

   • Walker H. Land Jr., J. David Schaffer

   Pages 157-185

8. Bayesian Probabilistic Neural Network (BPNN)

   • Walker H. Land Jr., J. David Schaffer

   Pages 187-210

9. Machine Intelligence Mixture of Experts and Bayesian Networks

   • Walker H. Land Jr., J. David Schaffer

   Pages 211-248

10. Quantifying Uncertainty

    • Walker H. Land Jr., J. David Schaffer

    Pages 249-262

11. Back Matter

    Pages 263-269

    PDF

This volume presents several machine intelligence technologies, developed over recent decades, and illustrates how they can be combined in application. One application, the detection of dementia from patterns in speech, is used throughout to illustrate these combinations. This application is a classic stationary pattern detection task, so readers may easily see how these combinations can be applied to other similar tasks. The expositions of the methods are supported by the basic theory they rest upon, and their application is clearly illustrated. The book’s goal is to allow readers to select one or more of these methods to quickly apply to their own tasks.

• Includes a variety of machine intelligent technologies and illustrates how they can work together

• Shows evolutionary feature subset selection combined with support vector machines and multiple classifiers combined

• Includes a running case study on intelligent processing relating to Alzheimer’s / dementia detection, in addition to several applications of the machine hybrid algorithms 
  

  
  

• Artificial intelligence
• Machine learning
• Evolutionary computation
• Genetic algorithms
• Feature subset selection
• Support vector machine
• Learning classifier systems
• Ensemble methods
• Generalized regression neural network (GRNN) oracle
• Bayesian networks

• Binghamton University, Bowie, USA

  Walker H. Land Jr.

• Binghamton University, Binghamton, USA

  J. David Schaffer

Professor Walker Land Jr. performed twenty years of classified military research for IBM, none of which can be discussed here. He retired from IBM in 1990 and joined Binghamton University for 26 years, retiring a second time at the rank of Research Professor in 2014. He is known as one of the prime developers of the GRNN oracle ensemble method for learning classifier systems. He also made contributions to the original TIROS satellite system, the forerunner of the current weather satellite system, as well as made original contributions to the 200 and 500 series Saturn/Apollo lunar flyby and landing programs.

Professor J David Schaffer published many years on genetic algorithms. He retired as Research Fellow after 25 years with Philips Research. He has a citation index of 12000 (Google Scholar), holds 43 issued US patents and was designated a Pioneer in Evolutionary Computation by the IEEE Computational Intelligence Society in 2012. He serves on the editorial board of the Evolutionary Computation Journal, and on the steering committee for the bi-annual conference series Evolutionary Multiobjective Optimization (EMO).

Policies and ethics