We apply a DNA-based massively parallel exhaustive search to solving the computational learning problems of DNF (disjunctive normal form) Boolean formulae. Learning DNF formulae from examples is one of the most important open problems in computational learning theory and the problem of learning 3-term DNF formulae is known as intractable if RP ≠ NP. We propose new methods to encode any k-term DNF formula to a DNA strand, evaluate the encoded DNF formula for a truth-value assignment by using hybridization and primer extension with DNA polymerase, and find a consistent DNF formula with the given examples. By employing these methods, we show that the class of k-term DNF formulae (for any constant k) and the class of general DNF formulae are efficiently learnable on DNA computer.
Second, in order for the DNA-based learning algorithm to be robust for errors in the data, we implement the weighted majority algorithm on DNA computers, called DNA-based majority algorithm via amplification (DNAMA), which take a strategy of ``amplifying'' the consistent (correct) DNA strands. We show a theoretical analysis for the mistake bound of the DNA-based majority algorithm via amplification, and imply that the amplification to ``double the volumes'' of the correct DNA strands in the test tube works well.
Unable to display preview. Download preview PDF.
- Adleman L (1994) Molecular computation of solutions to combinatorial problems. Science 266: 1021–1024Google Scholar
- Blumer A, Ehrenfeucht A, Haussler D and Warmuth MK (1989) Learnability and the Vapnik-Chervonenkis dimension. Journal of the ACM 36: 929–965Google Scholar
- Hagiya M, Arita M, Kiga D, Sakamoto K and Yokoyama S (1997) Towards parallel evaluation and learning of Boolean µ-formulas with molecules. In: Proceedings of Third Annual Meeting on DNA Based Computers, pp. 105–114Google Scholar
- Kearns M and Sebastian Seung H (1995) Learning from a population of hypotheses. Machine Learning 18: 255–276Google Scholar
- Kearns M and Vazirani U (1994) An Introduction to Computational Learning Theory. MIT Press, MassachusettsGoogle Scholar
- Lipton RJ (1995) DNA solution of hard computational problems. Science 268: 542–545Google Scholar
- Littlestone N and Warmuth MK (1994) The weighted majority algorithm. Information and Computation 108: 212–261Google Scholar
- Pitt L and Valiant LG (1988) Computational limitations on learning from examples. Journal of the ACM 35: 965–984.Google Scholar
- Păun Gh, Rozenberg G and Salomaa A (1998) DNA Computing. Springer-Verlag, HeidelbergGoogle Scholar
- Sakakibara Y and Suyama A (2000) Intelligent DNA chips: Logical operation of gene expression profiles on DNA computers. In: Genome Informatics 2000 (Proceedings of 11th Workshop on Genome Informatics), pp. 33–42. Universal Academy PressGoogle Scholar
- Valiant LG (1984) A theory of the learnable. Communications of the ACM 27: 1134–1142Google Scholar
- Winfree E (1998) Whiplash PCR for O(1) computing. In: Proceedings of Fourth Annual Meeting on DNA Based ComputersGoogle Scholar
- Yamamoto Y, Komiya S, Sakakibara Y and Husimi Y (2000) Application of 3SR reaction to DNA computer. In: Seibutu-Buturi 40(S198)Google Scholar