Quick search Find article
Quick search
Find article

Optimal unsupervised learning

T L H Watkin and J -P Nadal

Show affiliations


We introduce an inferential approach to unsupervised learning which allows us to define an optimal learning strategy. Applying these ideas to a simple, previously studied model, we show that it is impossible to detect structure in data until a critical number of examples have been presented-an effect which will be observed in all problems with certain underlying symmetries. Thereafter, the advantage of optimal learning over previously studied learning algorithms depends critically upon the distribution of patterns; optimal learning may be exponentially faster. Models with more subtle correlations are harder to analyse, but in a simple limit of one such problem we calculate exactly the efficacy of an algorithm similar to some used in practice, and compare it to that of the optimal prescription.


PACS

05.10.-a Computational methods in statistical physics and nonlinear dynamics

02.50.-r Probability theory, stochastic processes, and statistics

07.05.Mh Neural networks, fuzzy logic, artificial intelligence

MSC

82C32 Neural nets (See also 68T05, 91E40, 92B20)

68Q32 Computational learning theory (See also 68T05)

62H30 Classification and discrimination; cluster analysis (See also 68T10)

Subjects

Computational physics

Instrumentation and measurement

Statistical physics and nonlinear systems

Dates

Issue 6 (21 March 1994)



View by subject




Export








Please login to access our web services, or create an account if you don't yet have one.

You must have cookies enabled in your web browser to be able to login.

Username
Password

Forgotten your password? Get a new one here.