Edward R. Pantridge

  • Citations Per Year
Learn More
Programs evolved by genetic programming unfortunately often do not generalize to unseen data. Reliable synthesis of programs that generalize to unseen data is therefore an important open problem. We present evidence that smaller programs evolved using the PushGP system tend to generalize better over a range of program synthesis problems. Like in many(More)
The PushGP genetic programming system, which evolves programs expressed in the Push programming language, has been used for a variety of research projects and applications over its sixteen-year history. PushGP relies on an implementation of the Push language in a host language, and it is generally easiest to use PushGP in projects in which most other(More)
Genetic Programming, a kind of evolutionary computation and machine learning algorithm, is shown to benefit significantly from the application of vectorized data and the TensorFlow numerical computation library on both CPU and GPU architectures. The open source, Python <i>Karoo GP</i> is employed for a series of 190 tests across 6 platforms, with real-world(More)
A variety of inductive program synthesis (IPS) techniques have recently been developed, emerging from different areas of computer science. However, these techniques have not been adequately compared on general program synthesis problems. In this paper we compare several methods on problems requiring solution programs to handle various data types, control(More)
  • 1