D
Daw-Ran Liou
Researcher at National Taiwan University
Publications - 8
Citations - 397
Daw-Ran Liou is an academic researcher from National Taiwan University. The author has contributed to research in topics: Autoencoder & Pattern recognition (psychology). The author has an hindex of 2, co-authored 8 publications receiving 277 citations. Previous affiliations of Daw-Ran Liou include Cornell University.
Papers
More filters
Journal ArticleDOI
Autoencoder for words
TL;DR: A training method that encodes each word into a different vector in semantic space and its relation to low entropy coding is presented and is applied to the stylish analyses of two Chinese novels.
Posted Content
Syntactic sensitive complexity for symbol-free sequence
TL;DR: This work uses L-system to model the text sequence and derives the sequence complexity by calculating the complexity of its modeling system, which can sense certain quasi-regular structures and serves as a measure of regularity of the sequence.
Book ChapterDOI
Syntactic Sensitive Complexity for Symbol-Free Sequence
TL;DR: In this article, the authors used L-system to model the text sequence and obtained the sequence complexity by calculating the complexity of its modeling system, which can sense certain quasi-regular structures and serve as a measure of regularity of the sequence.
Book ChapterDOI
Autoencoder for polysemous word
TL;DR: This work presents a method to train multi-code for the polysemous word where each code represents a different meaning of the word and facilitates the operation of word-sense disambiguation in semantic space.
Journal Article
Finite geometrical relations loading in Hopfield model
TL;DR: This work rewrites geometrical relations and converts them into the Hopfield model to improve the matching result of the feature-to-feature adhesion method for hand-printed character recognition.