Computer Science – Neural and Evolutionary Computing
Scientific paper
2005-05-10
Computer Science
Neural and Evolutionary Computing
7 pages, 3 figures
Scientific paper
This paper discusses the notion of generalization of training samples over long distances in the input space of a feedforward neural network. Such a generalization might occur in various ways, that differ in how great the contribution of different training features should be. The structure of a neuron in a feedforward neural network is analyzed and it is concluded, that the actual performance of the discussed generalization in such neural networks may be problematic -- while such neural networks might be capable for such a distant generalization, a random and spurious generalization may occur as well. To illustrate the differences in generalizing of the same function by different learning machines, results given by the support vector machines are also presented.
No associations
LandOfFree
Distant generalization by feedforward neural networks 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 Distant generalization by feedforward neural networks, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Distant generalization by feedforward neural networks will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-312604