768 search results - page 105 / 154 » Information Geometry of Neural Networks |
ICASSP
2009
IEEE
15 years 6 months ago
2009
IEEE
In this paper we propose a new technique for robust keyword spotting that uses bidirectional Long Short-Term Memory (BLSTM) recurrent neural nets to incorporate contextual informa...
120
click to vote
ISCIS
2005
Springer
15 years 5 months ago
2005
Springer
Support Vector Machines (SVMs) have been applied to solve the classification of volatile organic compounds (VOC) data in some recent studies. SVMs provide good generalization perfo...
96
Voted
NECO
2007
14 years 11 months ago
2007
In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
ICIP
2009
IEEE
16 years 28 days ago
2009
IEEE
The DNA microarray images allow to analyze the natural gene expressions. In this paper we propose an advanced method to efficiently address the imaging storage as well as the perf...
112
click to vote
ISBI
2002
IEEE
16 years 17 days ago
2002
IEEE
In this paper we summarize our results for two classes of hierarchical multi-scale models that exploit contextual information for detection of structure in mammographic imagery. T...