Abstract
Any sequential machine M represents a function fM from input sequences to output symbols. A function f is representable if some finite-state sequential machine represents it. The function fM is called an n-th order approximation to a given function f if fM is equal to f for all input sequences of length less than or equal to n. It is proved that, for an arbitrary nonrepresentable function f, there are infinitely many n such that any sequential machine representing an nth order approximation to f has more than n/2 + 1 states. An analogous result is obtained for two-way sequential machines and, using these and related results, lower bounds are obtained for two-way sequential machines and, using these and related results, lower bounds are obtained on the amount of work tape required online and offline Turing machines that compute nonrepresentable functions.
- 1 RABIN, M. 0., AND SCOTT, D. Finite automata and their decision problems. IBM J. Res. Develop. 8, 2 (April 1959), 114-125.Google Scholar
- 2 SHEPHERDSON, J. C. The reduction of two-way automata to one-way automata, iBM J. Res. Develop. 3, 2 (April 1959), 198-220.Google Scholar
- 3 STEARNS, R. E., HAWrMANm, J., AND LEWIS, P. M., II. Hierarchies of memory limited computations. Proc. Sixth Annual Syrup. Switching Circuit Theory and Logical Design, Ann Arbor, Mich., 1965, pp. 179-190.Google Scholar
- 4 MOORE, E. F. Gedanken-experiments on sequential machines. In Shannon, C. E., and McCarthy, J. (Eds.), Automata Studies Ann. Math. Studies No. 341, Princeton U. Press, Princeton, N. J., 1956, pp. 129-153.Google Scholar
- 5 Konig, D. Theorie der Endlichen und Unendlichen Graphen. Chelsea Publishing Co., New York, 1950.Google Scholar
- 6 R0SENBERG, A.L. On n-tape finite-state acceptors. Proc. Fifth Annual Symp. Switching Circuit Theory and Logical Design, Princeton, N. J., 1964, pp. 76-81.Google Scholar
Index Terms
- Some Bounds on the Storage Requirements of Sequential Machines and Turing Machines
Recommendations
PAC-Bayes bounds for twin support vector machines
Twin support vector machines are regarded as a milestone in the development of support vector machines. Compared to standard support vector machines, they learn two nonparallel hyperplanes rather than one as in standard support vector machines for ...
Radius margin bounds for support vector machines with the RBF kernel
An important approach for efficient support vector machine (SVM) model selection is to use differentiable bounds of the leave-one-out (loo) error. Past efforts focused on finding tight bounds of loo (e.g., radius margin bounds, span bounds). However, ...
Sparseness of support vector machines—some asymptotically sharp bounds
NIPS'03: Proceedings of the 16th International Conference on Neural Information Processing SystemsThe decision functions constructed by support vector machines (SVM's) usually depend only on a subset of the training set—the so-called support vectors. We derive asymptotically sharp lower and upper bounds on the number of support vectors for several ...
Comments