Sciweavers

108 search results - page 17 / 22
» A Sparse Coding Based Similarity Measure
Sort
View
IJDE
2007
123views more  IJDE 2007»
13 years 7 months ago
Identifying Authorship by Byte-Level N-Grams: The Source Code Author Profile (SCAP) Method
Source code author identification deals with identifying the most likely author of a computer program, given a set of predefined author candidates. There are several scenarios whe...
Georgia Frantzeskou, Efstathios Stamatatos, Stefan...
TASLP
2008
201views more  TASLP 2008»
13 years 7 months ago
Syntactically Lexicalized Phrase-Based SMT
Abstract--Until quite recently, extending Phrase-based Statistical Machine Translation (PBSMT) with syntactic knowledge caused system performance to deteriorate. The most recent su...
Hany Hassan, Khalil Sima'an, Andy Way
TNN
2008
106views more  TNN 2008»
13 years 7 months ago
Unsupervised Segmentation With Dynamical Units
In this paper, we present a novel network to separate mixtures of inputs that have been previously learned. A significant capability of the network is that it segments the componen...
A. Ravishankar Rao, Guillermo A. Cecchi, Charles C...
BIOADIT
2006
Springer
13 years 11 months ago
Attractor Memory with Self-organizing Input
We propose a neural network based autoassociative memory system for unsupervised learning. This system is intended to be an example of how a general information processing architec...
Christopher Johansson, Anders Lansner
JMLR
2010
129views more  JMLR 2010»
13 years 2 months ago
Expectation Truncation and the Benefits of Preselection In Training Generative Models
We show how a preselection of hidden variables can be used to efficiently train generative models with binary hidden variables. The approach is based on Expectation Maximization (...
Jörg Lücke, Julian Eggert