Learn More
  • Tina Yu
  • Genetic Programming and Evolvable Machines
  • 2001
We present a novel approach using higher-order functions and λ abstraction to evolve recursive and modular programs. Moreover, a new term “structure abstraction” is introduced to describe the property emerged from the higher-order function program structure. We test this technique on the general even-parity problem. The results indicate that this approach(More)
Many optimization problems require the satisfaction of constraints in addition to their objectives. When using an evolutionary algorithm to solve such problems, these constraints can be enforced in many different ways to ensure that legal solutions (phenotypes) are evolved. We have identified eleven ways to handle constraints within various stages of an(More)
Genetic Programming is increasing in popularity as the basis for a wide range of learning algorithms. However, the technique has to date only been successfully applied to modest tasks because of the performance overheads of evolving a large number of data structures, many of which do not correspond to a valid program. We address this problem directly and(More)
In this study we investigated the effects of the angiogenesis inhibitor TNP-470 on human pancreatic cancer cells in vitro and in vivo. The action of TNP-470 on vascular endothelial growth factor (VEGF) was also assessed. In vitro human pancreatic cancer cells (MIAPaCa-2, AsPC-1, and Capan-1), and human umbilical vein endothelial cells (HUVEC) were exposed(More)
Types have been introduced to Genetic Programming (GP) by researchers with different motivation. We present the concept of types in GP and introduce a typed GP system, PolyGP, that supports polymorphism through the use of three different kinds of type variable. We demonstrate the usefulness of this kind of polymorphism in GP by evolving two polymorphic(More)
An evolutionary system that supports the interaction of neutral and adaptive mutations is investigated. Experimental results on a Boolean function and needle-in-haystack problems show that this system enables evolutionary search to find better solutions faster. Through a novel analysis based on the ratio of neutral to adaptive mutations, we identify this(More)
We investigate neutrality in the simple Genetic Algorithms (SGA) and in our neutrality-enabled evolutionary system using the OneMax problem. The results show that with the support of limited neutrality, SGA is less effective than our system where a larger amount of neutrality is supported. In order to understand the role of neutrality in evolutionary search(More)
Keywords: We applied genetic programming with a lambda abstraction module mechanism to learn technical trading rules based on S&P 500 index from 1982 to 2002. The results show strong evidence of excess returns over buy-and-hold after transaction cost. The discovered trading rules can be interpreted easily; each rule uses a combination of one to four widely(More)