151 search results - page 2 / 31 » Structured Training for Neural Network Transition-Based Pars... |
ACL
2004
13 years 6 months ago
2004
Discriminative methods have shown significant improvements over traditional generative methods in many machine learning applications, but there has been difficulty in extending th...
ENGL
2008
13 years 5 months ago
2008
dynamic analysis of structures for earthquake induced loads is very expensive in terms of the computational burden. In this study, to reduce the computational effort a new neural s...
IJCNN
2000
IEEE
13 years 9 months ago
2000
IEEE
In this paper we present the growing hierarchical self-organizing map. This dynamically growing neural network model evolves into a hierarchical structure according to the requirem...
NAACL
2007
13 years 6 months ago
2007
Previous work on discourse parsing has mostly relied on surface syntactic and lexical features; the use of semantics is limited to shallow semantics. The goal of this thesis is to...
NN
2011
Springer
12 years 8 months ago
2011
Springer
Neurodynamical models of working memory (WM) should provide mechanisms for storing, maintaining, retrieving, and deleting information. Many models address only a subset of these a...