Automatic Functions, Linear Time and Learning
The present work determines the exact nature of linear time computable notions which characterise automatic functions (those whose graphs are recognised by a finite automaton). The paper also determines which type of linear time notions permit full learnability for learning in the limit of automatic classes (families of languages which are uniformly recognised by a finite automaton). In particular it is shown that a function is automatic iff there is a one-tape Turing machine with a left end which computes the function in linear time where the input before the computation and the output after the computation both start at the left end. It is known that learners realised as automatic update functions are restrictive for learning. In the present work it is shown that one can overcome the problem by providing work-tapes additional to a resource-bounded base tape while keeping the update-time to be linear in the length of the largest datum seen so far. In this model, one additional such worktape provides additional learning power over the automatic learner model and the two-work-tape model gives full learning power.
KeywordsTuring Machine Inductive Inference Finite Automaton Input Symbol Input Word
Unable to display preview. Download preview PDF.
- 3.Blumensath, A., Grädel, E.: Automatic structures. In: 15th Annual IEEE Symposium on Logic in Computer Science (LICS), pp. 51–62 (2000)Google Scholar
- 7.Hartmanis, J.: Computational complexity of one-tape Turing machine computations. Journal of the Association of Computing Machinery 15, 411–418 (1968)Google Scholar
- 8.Hennie, F.C.: Crossing sequences and off-line Turing machine computations. In: Sixth Annual Symposium on Switching Circuit Theory and Logical Design, pp. 168–172 (1965)Google Scholar
- 11.Jain, S., Ong, Y.S., Pu, S., Stephan, F.: On automatic families. In: Proceedings of the eleventh Asian Logic Conference in Honour of Professor Chong Chitat on his Sixtieth Birthday, pp. 94–113. World Scientific (2012)Google Scholar
- 12.Jain, S., Osherson, D.N., Royer, J.S., Sharma, A.: Systems That Learn, 2nd edn. MIT Press (1999)Google Scholar
- 16.Odifreddi, P.: Classical Recursion Theory. Studies in Logic and the Foundations of Mathematics, vol. II, 143. Elsevier (1999)Google Scholar
- 17.Osherson, D., Stob, M., Weinstein, S.: Systems That Learn, An Introduction to Learning Theory for Cognitive and Computer Scientists. Bradford — The MIT Press, Cambridge, Massachusetts (1986)Google Scholar