摘要 |
A data processing apparatus is operated to optimize the amount of information represented by entries in a database. The operation comprises forming prior distributions over the parameters of entries in the database and subjecting a potential entry for the database to a process of evaluation. The evaluation includes, (a) sampling parameters from the prior distributions, (b) calculating a utility function from the samples and from the potential entry, and (c) calculating a utility value from the utility function. The process of evaluation is repeated for each of a plurality of further potential entries and the potential entry having the highest calculated utility value is selected.
|