UNSUPERVISED NEURAL NETWORK BASED FEATURE EXTRACTION USING WEAK TOP-DOWN CONSTRAINTS Herman Kamper1,2 , Micha Elsner3 , Aren Jansen4 , Sharon Goldwater2 1 CSTR and 2 ILCC, School of Informatics, University of Edinburgh,

First Page		Document Content
Date: 2015-09-29 11:06:25 Machine learning Artificial neural networks Artificial intelligence Learning Applied mathematics Computational neuroscience Cybernetics Computational statistics Autoencoder Speech recognition Backpropagation Supervised learning		UNSUPERVISED NEURAL NETWORK BASED FEATURE EXTRACTION USING WEAK TOP-DOWN CONSTRAINTS Herman Kamper1,2 , Micha Elsner3 , Aren Jansen4 , Sharon Goldwater2 1 CSTR and 2 ILCC, School of Informatics, University of Edinburgh, Add to Reading List Source URL: www.cstr.ed.ac.uk Download Document from Source Website File Size: 864,20 KB Share Document on Facebook

	Syntax-Directed Variational Autoencoder for Molecule Generation Hanjun Dai1* , Yingtao Tian2* , Bo Dai1 , Steven Skiena2 , Le Song1 1 College of Computing, Georgia Institute of Technology 2 DocID: 1vlR1 - View Document
	Semi-Supervised Recursive Autoencoder Si Chen and Yufei Wang Department of Electrical and Computer Engineering University of California San Diego {sic046, yuw176}@ucsd.edu DocID: 1v727 - View Document
	An Autoencoder Approach to Learning Bilingual Word Representations Sarath Chandar A P1 ∗ , Stanislas Lauly2 ∗ , Hugo Larochelle2 , Mitesh M Khapra3 , Balaraman Ravindran1 , Vikas Raykar3 , Amrita Saha3 1 DocID: 1v23p - View Document
	On Nonparametric Guidance for Learning Autoencoder Representations Jasper Snoek University of Toronto DocID: 1uwmD - View Document
	arXiv:1610.00291v1 [cs.CV] 2 OctDeep Feature Consistent Variational Autoencoder Xianxu Hou University of Nottingham, Ningbo China DocID: 1tDNC - View Document