Sciweavers

161 search results - page 3 / 33
» Transforming general networks into feed-forward by using tur...
Sort
View
ICASSP
2011
IEEE
12 years 11 months ago
Parallel Transformation Network features for speaker recognition
The use of speaker adaptation transforms as features for speaker recognition is an appealing alternative to conventional short-term cepstral features. In general, this kind of met...
Alberto Abad, Jordi Luque, Isabel Trancoso
MMMACNS
2005
Springer
14 years 26 days ago
Networks, Markov Lie Monoids, and Generalized Entropy
The continuous general linear group in n dimensions can be decomposed into two Lie groups: (1) an n(n-1) dimensional ‘Markov type’ Lie group that is defined by preserving the ...
Joseph E. Johnson
AINA
2004
IEEE
13 years 11 months ago
Using the Extension Function of XSLT and DSL to Secure XML Documents
XSLT is a very popular and flexible language for transforming XML documents which provides a powerful implementation of a tree-oriented transformation language for transmuting ins...
Tao-Ku Chang, Gwan-Hwan Hwang
JMLR
2012
11 years 9 months ago
Deep Learning Made Easier by Linear Transformations in Perceptrons
We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Tapani Raiko, Harri Valpola, Yann LeCun
AGI
2008
13 years 8 months ago
Probabilistic Quantifier Logic for General Intelligence: An Indefinite Probabilities Approach
: Indefinite probabilities are a novel technique for quantifying uncertainty, which were created as part of the PLN (Probabilistic Logic Networks) logical inference engine, which i...
Matthew Iklé, Ben Goertzel