Speed prior explained

The speed prior is a complexity measure similar to Kolmogorov complexity, except that it is based on computation speed as well as programlength.^[1] The speed prior complexity of a program is its size in bits plus the logarithm of the maximum time we are willing to run it to get a prediction.

When compared to traditional measures, use of the SpeedPrior has the disadvantage of leading to less optimal predictions, andthe advantage of providing computable predictions.

See also

• Computational complexity theory
• Inductive inference
• Minimum message length
• Minimum description length

References

1. Schmidhuber, J. (2002) The Speed Prior: A New Simplicity Measure Yielding Near-Optimal Computable Predictions. In J. Kivinen and R. H. Sloan, editors, Proceedings of the 15th Annual Conference on Computational Learning Theory (COLT 2002). Lecture Notes in Artificial Intelligence, pages 216--228. Springer.[ftp://ftp.idsia.ch/pub/juergen/coltspeed.pdf]

External links

• Speed Prior web site