|
NeuroCOLT
Technical Report NC-TR-95-046
Learning Model Bias
Jonathan Baxter
Royal Holloway
University of London
Abstract
In this paper the problem of learning appropriate domain-specific
bias is addressed. It is shown that this can be achieved by learning
many related tasks from the same domain, and a sufficient bound is
given on the number tasks that must be learnt. A corollary of the
theorem is that in appropriate domains the number of examples required
per task for good generalisation when learning $n$ tasks scales like
$\frac1n$. An experiment providing strong qualitative support for
the theoretical results is reported.
Download Compressed Postscript
|