---
title: "Learning to Represent Codons: A Challenge Problem for Constructive Induction"
authors:
  - "Mark W. Craven"
  - "Jude W. Shavlik"
doi: ""
url: "https://ijcai.org/proceedings/1993/182"
pdf: "https://ijcai.org/proceedings/1993/0182.pdf"
venue: "Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence"
year: 1993
pages: "1319-1323"
track: "Neural Networks"
keywords:
---

# Learning to Represent Codons: A Challenge Problem for Constructive Induction

Mark W. Craven, Jude W. Shavlik

*Proceedings of the Thirteenth International Joint Conference on Artificial Intelligence*, pages 1319-1323.

## Abstract

The ability of an inductive learning system to find a good solution to a given problem is dependent upon the representation used for the features of the problem . Systems that perform constructive induction are able to change their representation by constructing new features . We describe an important, real-world problem - finding genes in DNA - that we believe offers an interesting challenge to constructiveinduction researchers. We report experiments that demonstrate that: (1) two different input representations for this task result in significantly different generalization performance for both neural networks and decision trees; and (2) both neural and symbolic methods for constructive induction fail to bridge the gap between these two representations. We believe that this real-world domain provides an interesting challenge problem for constructive induction because the relationship between the two representations is well known, and because th e representational shift involved in constructing the better representation is not imposing.