https://scholars.lib.ntu.edu.tw/handle/123456789/115349
Title: | Resolving hidden representations | Authors: | CHENG-YUAN LIOU Cheng Wei-Chen |
Issue Date: | 2008 | Start page/Pages: | Part-II | Source: | Lecture Notes in Computer Science 4985 | 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. |
URI: | http://ntur.lib.ntu.edu.tw//handle/246246/221404 https://www.scopus.com/record/display.uri?eid=2-s2.0-54049153273&origin=resultslist |
ISSN: | 03029743 | DOI: | 10.1007/978-3-540-69162-4_27 | SDG/Keyword: | Classification tasks; Data patterns; Hidden layers; Kernel functions; Layer-by-layer; Multiple classes; Novel techniques; Pattern representations |
Appears in Collections: | 資訊工程學系 |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.