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

  title={Learning to Represent Codons: A Challenge Problem for Constructive Induction.},
  author={Mark Craven and Jude W. Shavlik},
  booktitle={IJCAI 1993},
The ability of an inductive learning system to nd 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 { nding genes in DNA { that we believe offers an interesting challenge to constructive-induction researchers. We report experiments that demonstrate that: (1) two diierent input… CONTINUE READING
Highly Cited
This paper has 32 citations. REVIEW CITATIONS

From This Paper

Figures, tables, and topics from this paper.


Publications citing this paper.


Publications referenced by this paper.
Showing 1-7 of 7 references

Connectionist learningprocedures

G. E. Hinton.
Arti cial Intelligence

Determination of eucaryotic protein codingregions using neural networks and information theory

A. Lapedes, K. Sirotkin
Journal of Molecular Biology

Uberbacher andR . J . Mural . Locating protein coding regions in humanDNA sequences by a multiple sensor { neural networkapproach

C. E.
Proc . of the National Academy of Sciences

Similar Papers

Loading similar papers…