Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise

Details Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise

1997-10-08

arxiv.org/abs/cond-mat/9710074v1

Physics

Condensed Matter

Disordered Systems and Neural Networks

LaTex, 39 pages, including 12 attached .eps-figure pages. To appear in J. Phys. A

Scientific paper

10.1088/0305-4470/30/24/017

We extend our study of phase transitions in the generalization behaviour of multilayer perceptrons with non-overlapping receptive fields to the problem of the influence of noise, concerning e.g. the input units and/or the couplings between the input units and the hidden units of the second layer (='input noise'), or the final output unit (='output noise'). Without output noise, the output itself is given by a general, permutation-invariant Boolean function of the outputs of the hidden units. As a result we find that the phase transitions, which we found in the deterministic case, mostly persist in the presence of noise. The influence of the noise on the position of the phase transition, as well as on the behaviour in other regimes of the loading parameter $\alpha$, can often be described by a simple rescaling of $\alpha$ depending on strength and type of the noise. We then consider the problem of the optimal noise level for Gibbsian and Bayesian learning, looking on replica symmetry breaking as well. Finally we consider the question why learning with errors is useful at all.

Affiliated with

Also associated with

No associations

Rating

Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Phase transitions in the generalization behaviour of multilayer perceptrons: II. The influence of noise will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-129792