Resolving hidden representations
Resource
LNCS 4985, Part II, pp. 254–263, 2008
Journal
Lecture Notes in Computer Science 4985
Pages
Part-II
Date Issued
2008
Date
2008
Author(s)
Cheng Wei-Chen
Abstract
This paper presents a novel technique to separate the pattern representation in each hidden layer to facilitate many classification tasks. This technique requires that all patterns in the same class will have near representions and the patterns in different classes will have distant representions. This requirement is applied to any two data patterns to train a selected hidden layer of the MLP or the RNN. The MLP can be trained layer by layer feedforwardly to accomplish resolved representations. The trained MLP can serve as a kind of kernel functions for categorizing multiple classes. © 2008 Springer-Verlag Berlin Heidelberg.
Other Subjects
Classification tasks; Data patterns; Hidden layers; Kernel functions; Layer-by-layer; Multiple classes; Novel techniques; Pattern representations
Type
conference paper
File(s)![Thumbnail Image]()
Loading...
Name
10.pdf
Size
23.19 KB
Format
Adobe PDF
Checksum
(MD5):5e64641a7c07f4e7a79e4439fc4f5e1b