Algorithm **GUESS** is almost identical to a probabilistic search
algorithm used in previous work on applied inductive inference
[#!Schmidhuber:95kol!#,#!Schmidhuber:97nn!#]. The
programs generated by the previous algorithm, however,
were not bitstrings but written in an assembler-like language;
their runtimes had an upper bound, and the
program outputs were evaluated as to whether they represented solutions
to externally given tasks.

Using a small set of exemplary training examples, the system discovered the weight matrix of an artificial neural network whose task was to map input data to appropriate target classifications. The network's generalization capability was then tested on a much larger unseen test set. On several toy problems it generalized extremely well in a way unmatchable by traditional neural network learning algorithms.

The previous papers, however, did not explicitly establish
the above-mentioned relation between ``optimal'' resource
bias and **GUESS**.

Related links: In the beginning was the code! - Zuse's thesis - Life, the universe, and everything - Generalized Algorithmic Information - Speed Prior - The New AI