**Hybrid SA Applications**

198 Simulated Annealing – Advances, Applications and Hybridizations

markers. Molecular Ecology 2006; 15 1657-1667.

Wageningen Academic Publishers; 2007 p 167-193.

to Livestock Production, Belo Horizonte; 2006 p 120-121.

programs. Genetics 2006;173 483-96.

2003;165 885-894.

2009;92 433-43.

124 369-376.

Production 2009;3 1339-1346.

[18] Fernàndez J., Toro M.A., Caballero, A.. Fixed contributions designs versus minimization of global coancestry to contrai inbreeding in small populations. Genetics

[19] Fernàndez J. and Toro M.A.. A new method to estimate relatedness from molecular

[20] Oliehoek P.A., Windig J.J., Van Arendonk J.A.,Bijma, P., Estimating relatedness between individuals in generai populations with a focus on their use in conservation

[21] Hayes, B.J., Bowman, P.J., Chamberlain, A.J. and Goddard, M.E. Invited review: Genomic selection in dairy cattle: progress and challenges. Journal of Dairy Science

[22] Meuwissen T.H.E. Operation of conservation schemes. In: Oldenbroek, K (ed.) Utilisation and conservation of farm animal genetic resources. Wageningen:

[23] Meuwissen T.H.E.. GENCONT: An operational tool for controlling inbreeding in selection and conservation schemes. Proceedings of 7th World Congress on Genetics

[25] Crow J.F. and Kimura, M., 1972 An introduction to population genetics theory. Harper and Row; New York. Daetwyler, H.D., Villanueva, B., Btjma, P., Woolliams, J.A.. Inbreeding in Genome-Wide Selection. Journal of Animal Breeding and Genetics 2007;

[26] Henryon M., Sorensen A.C. and Berg P. Mating animals by minimising the covariance between ancestral contributions generates more genetic gain without increasing rate of inbreeding in breeding schemes with optìmum-contribution selection. Animal

[27] Sonesson A.K., Gjerde B., Meuwissen T.H.E. Truncation selection of BLUP-EBV and

phenotypic values in fish breeding schemes. Aquaculture 2005; 243:61-68.

Applied to Livestock Production, Montpellier,19-23 August 2002; 33 769-770. [24] Berg P., Nielsen I., and Sorensen M.K. Computing realized and predicting optimal genetic contributions by ÈVA. Proceedings of 8th World Congress on Genetics Applied

**Chapter 0**

**Chapter 10**

**Simulated Annealing Evolution**

Sergio Ledesma, Jose Ruiz and Guadalupe Garcia

Additional information is available at the end of the chapter

Artificial intelligence (AI) is a branch of computer science that seeks to create intelligence. While humans have been using computers to simplify several tasks, AI provides new options to use computers. For instance, voice recognition software uses AI to transform the sounds to the equivalent text words. There are several techniques that AI includes. An artificial neural

Humans use their intelligence to solve complex problems and perform daily tasks. Human intelligence is provided by the brain. Small processing units called neurons are the main components of the human brain. ANNs try to imitate partially some of the human brain behavior. Thus, artificial neurons are designed to mimic the activities of biological neurons. Humans learn by experience: they are exposed to events that encourage their brains to acquire knowledge. Similarly, ANNs extract information from a data set; this set is typically called the training set and is organized in the same way that schools design their courses' content. ANNs provide an excellent way to understand better biological neurons. In practice, some problems may be described by a data set. For instance, an ANN is typically trained using a data set. For some problems, building a data set may be very difficult or sometimes impossible as the data

Simulated annealing (SA) is a method that can be used to solve an ample set of optimization problems. SA is a very robust technique as it is not deceived with local minima. Additionally, a mathematical model is not required to apply SA to solve most optimization problems.

This chapter explores the use of SA to train an ANN without the requirement of a data set. The chapter ends with a computer simulation where an ANN is used to drive a car. Figure 1 shows the system architecture. SA is used to provide a new set of weights to the ANN. The ANN controls the acceleration and rotation speed of the car. The car provides feedback by sending vision information to the ANN. The distance traveled along the road from the *Start* is used by the method of SA. At the beginning of the simulation the ANN does not know how to drive the car. As the experiment continues, SA is used to train the ANN. Each time the

and reproduction in any medium, provided the original work is properly cited.

©2012 Ledesma et al., licensee InTech. This is an open access chapter distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0),which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly

© 2012 The Author(s). Licensee InTech. This chapter is distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution,

http://dx.doi.org/10.5772/50176

network (ANN) is one of these techniques.

set has to capture all possible cases of the experiment.

cited.

**1. Introduction**
