Sciweavers

10 search results - page 1 / 2
» Understanding the difficulty of training deep feedforward ne...
Sort
View
JMLR
2010
151views more  JMLR 2010»
12 years 10 months ago
Understanding the difficulty of training deep feedforward neural networks
Whereas before 2006 it appears that deep multilayer neural networks were not successfully trained, since then several algorithms have been shown to successfully train them, with e...
Xavier Glorot, Yoshua Bengio
JMLR
2012
11 years 6 months ago
Deep Boltzmann Machines as Feed-Forward Hierarchies
The deep Boltzmann machine is a powerful model that extracts the hierarchical structure of observed data. While inference is typically slow due to its undirected nature, we argue ...
Grégoire Montavon, Mikio L. Braun, Klaus-Ro...
PAKDD
1998
ACM
158views Data Mining» more  PAKDD 1998»
13 years 7 months ago
Data Mining Using Dynamically Constructed Recurrent Fuzzy Neural Networks
Abstract. Approaches to data mining proposed so far are mainly symbolic decision trees and numerical feedforward neural networks methods. While decision trees give, in many cases, ...
Yakov Frayman, Lipo Wang
ICASSP
2011
IEEE
12 years 7 months ago
Deep Belief Networks using discriminative features for phone recognition
Deep Belief Networks (DBNs) are multi-layer generative models. They can be trained to model windows of coefficients extracted from speech and they discover multiple layers of fea...
Abdel-rahman Mohamed, Tara N. Sainath, George Dahl...
CIMCA
2005
IEEE
13 years 9 months ago
Hybrid Neural Networks for Immunoinformatics
Hybrid set of optimally trained feed-forward, Hopfield and Elman neural networks were used as computational tools and were applied to immunoinformatics. These neural networks ena...
Khrizel B. Solano, Tolja Djekovic, Mohamed Zohdy