Bias and No Free Lunch in Formal Measures of Intelligence

Bias and No Free Lunch in Formal Measures of Intelligence

This paper shows that a constraint on universal Turing machines is necessary for Legg's and Hutter's formal measure of intelligence to be unbiased. Their measure, defined in terms of Turing machines, is adapted to finite state machines. A No Free Lunch result is proved for the finite version of the measure.

If the inline PDF is not rendering correctly, you can download the PDF file here.

  • Auger, A. and O. Teytaud. Continuous lunches are free! Proceedings of the 9th annual conference on Genetic and evolutionary computation (ACM SIGEVO 1997), pages 916-922.

  • Hutter, M. Universal Artificial Intelligence: Sequential Decisions based on Algorithmic Probability. Springer, Berlin. 2004. 300 pages.

  • Legg, S. and M. Hutter. Proc. A Formal Measure of Machine Intelligence. 15th Annual Machine Learning Conference of Belgium and The Netherlands (Benelearn 2006), pages 73-80.

  • Li, M. and P. Vitányi, An Introduction to Kolmogorov Complexity and Its Applications, 2nd ed.. Springer, New York, 1997. 637 pages.

  • Lloyd, S. Computational Capacity of the Universe. Phys. Rev. Lett. 88 (2002) 237901.

  • Rice, H. G. Classes of Recursively Enumerable Sets and Their Decision Problems. Trans. Amer. Math. Soc. 74, pages 358-366. 1953.

  • Wang, P. Non-Axiomatic Reasoning System — Exploring the essence of intelligence. PhD Dissertation, Indiana University Comp. Sci. Dept. and the Cog. Sci. Program, 1995.

  • Wolpert, D. and W. Macready, No Free Lunch Theorems for Optimization. IEEE Transactions on Evolutionary Computation 1, 67. 1997.


Journal + Issues