Related Experiment Video
Updated: Jul 5, 2026

Synthesis of Cyclic Polymers and Characterization of Their Diffusive Motion in the Melt State at the Single Molecule Level
Published on: September 26, 2016
Contrastive divergence in gaussian diffusions
1Institute for Neural Computation, University of California San Diego, La Jolla, CA 92093-0515, USA. movellan@mplab.ucsd.edu
Abstract:
This letter presents an analysis of the contrastive divergence (CD) learning algorithm when applied to continuous-time linear stochastic neural networks. For this case, powerful techniques exist that allow a detailed analysis of the behavior of CD. The analysis shows that CD converges to maximum likelihood solutions only when the network structure is such that it can match the first moments of the desired distribution. Otherwise, CD can converge to solutions arbitrarily different from the log-likelihood solutions, or they can even diverge. This result suggests the need to improve our theoretical understanding of the conditions under which CD is expected to be well behaved and the conditions under which it may fail. In, addition the results point to practical ideas on how to improve the performance of CD.
Related Concept Videos
Gauss's Law
Diffusion on Chromatography Columns
Longitudinal diffusion occurs when the solute molecules in the mobile phase diffuse from the more concentrated center of the chromatographic band to the more dilute regions on either side, both towards and against the flow direction. This...
Gauss's Law in Dielectrics
Divergence and Stokes' Theorems
Gauss's Law: Cylindrical Symmetry
Diffusion

