Volume 40, Number 3, November I 1997
|Page(s)||251 - 256|
|Published online||01 September 2002|
Unsupervised learning of distributions
Universität Augsburg, Memminger Str. 6, 86135 Augsburg, Germany
Accepted: 16 September 1997
We study unsupervised learning from non-uniformly distributed examples with a single symmetry-breaking orientation when both the distribution and the preferential direction are otherwise completely unknown. For asymptotically high dimensions N of the pattern space the distribution can be inferred exactly from p=O(N) examples up to a well-known remaining uncertainty in the preferential direction. We further discuss implications for supervised learning of a teacher perceptron with unknown transfer function, unsupervised learning with several preferential directions, and architecture optimization.
PACS: 07.05.Kf – Data analysis: algorithms and implementation; data management / 02.50.-r – Probability theory, stochastic processes, and statistics / 05.20.-y – Statistical mechanics
© EDP Sciences, 1997
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.