Quick search Find article
Quick search
Find article

Statistical mechanics of hypothesis evaluation

A D Bruce and D Saad

Show affiliations


Following ideas of Gull, Skilling and MacKay (1992), we develop and explore a statistical-mechanics framework through which one may assign values to the parameters of a model for a 'rule' (instanced, here, by the noisy linear perceptron), on the basis of data instancing the rule. The 'evidence' which the data offers in support of a given assignment, is likened to the free energy of a system with quenched variables (the data): the most probable (MAP) assignments of parameters are those which minimize this free-energy; tracking the free-energy minimum may lead to 'phase transitions' in the preferred assignments. We explore the extent to which the MAP assignments lead to optimal performance.


PACS

05.70.Ce Thermodynamic functions and equations of state

07.05.Mh Neural networks, fuzzy logic, artificial intelligence

MSC

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

82C26 Dynamic and nonequilibrium phase transitions (general)

Subjects

Instrumentation and measurement

Statistical physics and nonlinear systems

Dates

Issue 10 (21 May 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.