We present and relate recent results in prediction based on countable classes of either probability (semi-)distributions or base predictors. Learning by Bayes, MDL, and stochastic ...
We bound the future loss when predicting any (computably) stochastic sequence online. Solomonoff finitely bounded the total deviation of his universal predictor M from the true dis...
We show that Kolmogorov complexity and such its estimators as universal codes (or data compression methods) can be applied for hypothesis testing in a framework of classical mathe...
The problem of prediction future event given an individual sequence of past events is considered. Predictions are given in form of real numbers pn which are computed by some algori...
Multisource information theory in Shannon setting is well known. In this article we try to develop its algorithmic information theory counterpart and use it as the general framewo...
In the first part, we introduce binary representations of both lambda calculus and combinatory logic terms, and demonstrate their simplicity by providing very compact parser-inter...
We have found a method to automatically extract the meaning of words and phrases from the world-wide-web using Google page counts. The approach is novel in its unrestricted proble...