Computer Science – Learning
Scientific paper
2000-02-09
Computer Science
Learning
12 pages
Scientific paper
We construct new algorithms from scratch, which use the fourth order cumulant of stochastic variables for the cost function. The multiplicative updating rule here constructed is natural from the homogeneous nature of the Lie group and has numerous merits for the rigorous treatment of the dynamics. As one consequence, the second order convergence is shown. For the cost function, functions invariant under the componentwise scaling are choosen. By identifying points which can be transformed to each other by the scaling, we assume that the dynamics is in a coset space. In our method, a point can move toward any direction in this coset. Thus, no prewhitening is required.
Akuzawa Toshinao
Murata Noboru
No associations
LandOfFree
Multiplicative Nonholonomic/Newton -like Algorithm 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 Multiplicative Nonholonomic/Newton -like Algorithm, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Multiplicative Nonholonomic/Newton -like Algorithm will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-227873