Ambiguous model learning made unambiguous with 1/f priors

Details Ambiguous model learning made unambiguous with 1/f priors Ambiguous model learning made unambiguous with 1/f priors

2005-12-23

arxiv.org/abs/q-bio/0512040v1

NIPS 16, MIT Press, Cambridge (2004)

Biology

Quantitative Biology

Other Quantitative Biology

8 pages, 2 figures

Scientific paper

What happens to the optimal interpretation of noisy data when there exists more than one equally plausible interpretation of the data? In a Bayesian model-learning framework the answer depends on the prior expectations of the dynamics of the model parameter that is to be inferred from the data. Local time constraints on the priors are insufficient to pick one interpretation over another. On the other hand, nonlocal time constraints, induced by a $1/f$ noise spectrum of the priors, is shown to permit learning of a specific model parameter even when there are infinitely many equally plausible interpretations of the data. This transition is inferred by a remarkable mapping of the model estimation problem to a dissipative physical system, allowing the use of powerful statistical mechanical methods to uncover the transition from indeterminate to determinate model learning.

Affiliated with

Also associated with

No associations

Rating

Ambiguous model learning made unambiguous with 1/f priors 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 Ambiguous model learning made unambiguous with 1/f priors, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Ambiguous model learning made unambiguous with 1/f priors will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-697166