Creative Evolutionary Systems

Creative Evolutionary Systems

The Morgan Kaufmann Series in Artificial Intelligence
2002, Pages 275-298
Creative Evolutionary Systems

Chapter 10 - Genetic Programming: Biologically Inspired Computation That Exhibits Creativity in Producing Human-Competitive Results

https://doi.org/10.1016/B978-155860673-9/50048-3Get rights and content

Publisher Summary

One of the central challenges of computer science is to get a computer to solve a problem without programming it explicitly. The challenge is to create an automatic system whose input is a high-level statement of a problem's requirements and whose output is a satisfactory solution to the given problem. This challenge is the common goal of such fields of research as artificial intelligence and machine learning. Paraphrasing Arthur Samuel, this challenge addresses the question: How can computers are made to do what needs to be done, without being told exactly how to do it? As Samuel further explained: “The aim is to get machines to exhibit behavior, which if done by humans, would be assumed to involve the use of intelligence.” This chapter provides an affirmative answer to the following two questions: Starting only with a high-level statement of the problem's requirements, can computers automatically discover the solution to nontrivial problems? And, can automatically created solutions be competitive with the products of human creativity and inventiveness? In answering these questions, this chapter focuses on a biologically inspired domain-independent problem-solving technique of evolutionary computation, called genetic programming. For each problem, genetic programming automatically creates entities that improve on previously patented inventions, or duplicate the functionality of previously patented inventions or duplicate the functionality of previously patented inventions. The chapter also discusses the importance of illogic in achieving creativity and inventiveness.

References (0)

Cited by (0)

View full text