W
Wei-Chen Cheng
Researcher at National Taiwan University
Publications - 18
Citations - 507
Wei-Chen Cheng is an academic researcher from National Taiwan University. The author has contributed to research in topics: Manifold alignment & Manifold (fluid mechanics). The author has an hindex of 5, co-authored 18 publications receiving 385 citations. Previous affiliations of Wei-Chen Cheng include Academia Sinica.
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.
Book ChapterDOI
Manifold Construction by Local Neighborhood Preservation
Cheng-Yuan Liou,Wei-Chen Cheng +1 more
TL;DR: This work presents a neighborhood preservation method to construct the latent manifold that preserves the relative Euclidean distances among neighboring data points and its performance in preserving the local relationships is promising when compared with the methods, LLE and Isomap.
Book ChapterDOI
Resolving Hidden Representations
Cheng-Yuan Liou,Wei-Chen Cheng +1 more
TL;DR: A novel technique to separate the pattern representation in each hidden layer to facilitate many classification tasks and serve as a kind of kernel functions for categorizing multiple classes.
Proceedings ArticleDOI
Construct adaptive template array for magnetic resonance images
TL;DR: A novel method, transformation diversion, based on the ordered representations is proposed to improve the registration, which is a non-linear deformation, in a general manner.
Journal ArticleDOI
Segmentation of DNA using simple recurrent neural network
TL;DR: The distribution of prediction error indicates how the underlying hidden regularity of the genome sequences and the results are consistent with the finding of biologists: predicated protein coding features of SARS genome implies that the simple recurrent network is capable of providing new features for further biological studies when applied on genome studies.