Anti-pairing in learning of a neural network with redundant hidden units
Copyright policy )Anti-pairing in learning of a neural network with redundant hidden units
There is a study on learning from examples in a two-layered committee neural network by using replica theory. The number of hidden units of the student network is assumed larger than the number of hidden units in the target (teacher) network. Both networks have same number of input and output units. One introduces first some basics in statistical mechanics and infinite degeneracy's. Discussed are the permutation-symmetric state and permutation symmetry breaking phase. Monte Carlo simulation results are shown to be in agreement with the theoretical experiments.
- Myongji University Korea (Republic of)
neural network, Neural nets applied to problems in time-dependent statistical mechanics, anti-pairing, two-layered committee machine, Monte Carlo methods
neural network, Neural nets applied to problems in time-dependent statistical mechanics, anti-pairing, two-layered committee machine, Monte Carlo methods
selected citations These citations are derived from selected sources.This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).0 popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.Average influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).Average impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.Average
Citations provided by BIP!Popularity provided by BIP!