Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/mit-press/the-effect-of-noise-on-a-class-of-energy-based-learning-rules-xrWhDwz2DU
References
References for this paper are not available at this time. We will be adding them shortly, thank you for your patience.
- Publisher
- MIT Press
- Copyright
- © 2003 Massachusetts Institute of Technology
- ISSN
- 0899-7667
- eISSN
- 1530-888X
- DOI
- 10.1162/089976603321891837
- pmid
- 12816569
- Publisher site
- See Article on Publisher Site
Abstract
We study the selectivity properties of neurons based on BCM and kurtosis energy functions in a general case of noisy high-dimensional input space. The proposed approach, which is used for characterization of the stable states, can be generalized to a whole class of energy functions. We characterize the critical noise levels beyond which the selectivity is destroyed. We also perform a quantitative analysis of such transitions, which shows interesting dependency on data set size. We observe that the robustness to noise of the BCM neuron (Bienenstock, Cooper, & Munro, 1982; Intrator & Cooper, 1992) increases as a function of dimensionality. We explicitly compute the separability limit of BCM and kurtosis learning rules in the case of a bimodal input distribution. Numerical simulations show a stronger robustness of the BCM rule for practical data set size when compared with kurtosis.
Journal
Neural Computation – MIT Press
Published: Jul 1, 2003