Neurally Guided Genetic Programming for Turing Complete Programming by Example

Alexander Newton Wild, Barry Porter

Keywords: Code Synthesis, Neural Code Synthesis, Genetic Programming, Programming By Example

Abstract: The ability to synthesise source code from input/output examples allows nonexperts to generate programs, and experts to abstract away a wide range of simple programming tasks. Current research in this area has explored neural synthesis, SMT solvers, and genetic programming; each of these approaches is limited, however, often using highly specialised target languages for synthesis. In this paper we present a novel hybrid approach using neural networks to guide genetic programming (GP), which allows us to successfully synthesise code from just ten I/O examples in a generalised Turing complete target language, up to and including a sorting algorithm. We show that GP by itself is able to synthesise a set of simple programs, and show which hints (suggested lines of code for inclusion) are of most utility to GP in solving harder problems. Using a form of unstructured curriculum learning, we then demonstrate that neural networks can be used to determine when to make use of these high-utility hints for specific I/O problems and thus enable complex functions to be successfully synthesised. We apply our approach to two different problem sets: common array-to-array programs (including sorting), and a canvas drawing problem set inspired by So & Oh (2018).

One-sentence Summary: This paper demonstrates that the use of genetic programming, guided by neural networks to provide search hints, is able to synthesise complex programs in a Turing-complete language -- up to and including the synthesis of sorting algorithms.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=kZVFM_krJW