Physics – Condensed Matter – Disordered Systems and Neural Networks
Scientific paper
1997-05-19
Physics
Condensed Matter
Disordered Systems and Neural Networks
Latex 20 pages with 10 figures
Scientific paper
10.1103/PhysRevE.58.849
We investigate the generalization ability of a perceptron with non-monotonic transfer function of a reversed-wedge type in on-line mode. This network is identical to a parity machine, a multilayer network. We consider several learning algorithms. By the perceptron algorithm the generalization error is shown to decrease by the ${\alpha}^{-1/3}$-law similarly to the case of a simple perceptron in a restricted range of the parameter $a$ characterizing the non-monotonic transfer function. For other values of $a$, the perceptron algorithm leads to the state where the weight vector of the student is just opposite to that of the teacher. The Hebbian learning algorithm has a similar property; it works only in a limited range of the parameter. The conventional AdaTron algorithm does not give a vanishing generalization error for any values of $a$.We thus introduce a modified AdaTron algorithm which yields a good performance for all values of $a$. We also investigate the effects of optimization of the learning rate as well as of the learning algorithm. Both methods give excellent learning curves proportional to ${\alpha}^{-1}$. The latter optimization is related to the Bayes statistics and is shown to yield useful hints to extract maximum amount of information necessary to accelerate learning processes.
Inoue Jun'ichi
Kabashima Yoshiyuki
Nishimori Hidetoshi
No associations
LandOfFree
Generalization ability of a perceptron with non-monotonic transfer function 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 Generalization ability of a perceptron with non-monotonic transfer function, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Generalization ability of a perceptron with non-monotonic transfer function will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-530349