Sciweavers

ICASSP
2009
IEEE
14 years 1 months ago
Neural network based language models for highly inflective languages
Speech recognition of inflectional and morphologically rich languages like Czech is currently quite a challenging task, because simple n-gram techniques are unable to capture impo...
Tomas Mikolov, Jirí Kopecký, Lukas B...
ICANN
2009
Springer
14 years 1 months ago
Profiling of Mass Spectrometry Data for Ovarian Cancer Detection Using Negative Correlation Learning
This paper proposes a novel Mass Spectrometry data profiling method for ovarian cancer detection based on negative correlation learning (NCL). A modified Smoothed Nonlinear Energy ...
Shan He, Huanhuan Chen, Xiaoli Li, Xin Yao
ICANN
2009
Springer
14 years 1 months ago
Large-Scale Real-Time Object Identification Based on Analytic Features
Inspired by biological findings, we present a system that is able to robustly identify a large number of pre-trained objects in realtime. In contrast to related work, we do not res...
Stephan Hasler, Heiko Wersing, Stephan Kirstein, E...
ICANN
2009
Springer
14 years 1 months ago
Efficient Uncertainty Propagation for Reinforcement Learning with Limited Data
In a typical reinforcement learning (RL) setting details of the environment are not given explicitly but have to be estimated from observations. Most RL approaches only optimize th...
Alexander Hans, Steffen Udluft
ICANN
2007
Springer
14 years 1 months ago
An Efficient Method for Pruning the Multilayer Perceptron Based on the Correlation of Errors
Abstract. In this paper we present a novel method for pruning redundant weights of a trained multilayer Perceptron (MLP). The proposed method is based on the correlation analysis o...
Cláudio M. S. Medeiros, Guilherme De A. Bar...
ICANN
2007
Springer
14 years 1 months ago
Active Learning to Support the Generation of Meta-examples
Meta-Learning has been used to select algorithms based on the features of the problems being tackled. Each training example in this context, i.e. each meta-example, stores the feat...
Ricardo Bastos Cavalcante Prudêncio, Teresa ...
ICANN
2007
Springer
14 years 1 months ago
Estimation of Pointing Poses on Monocular Images with Neural Techniques - An Experimental Comparison
Poses and gestures are an important part of the nonverbal inter-human communication. In the last years many different methods for estimating poses and gestures in the field of Huma...
Frank-Florian Steege, Christian Martin, Horst-Mich...
ICANN
2007
Springer
14 years 1 months ago
Neural Network Approach for Mass Spectrometry Prediction by Peptide Prototyping
In todays bioinformatics, Mass spectrometry (MS) is the key technique for the identification of proteins. A prediction of spectrum peak intensities from pre computed molecular feat...
Alexandra Scherbart, Wiebke Timm, Sebastian Bö...
ICANN
2007
Springer
14 years 1 months ago
An Efficient Search Strategy for Feature Selection Using Chow-Liu Trees
Within the taxonomy of feature extraction methods, recently the Wrapper approaches lost some popularity due to the associated computational burden, compared to Embedded or Filter m...
Erik Schaffernicht, Volker Stephan, Horst-Michael ...
ICANN
2007
Springer
14 years 1 months ago
The Link Between Temporal Attention and Emotion: A Playground for Psychology, Neuroscience, and Plausible Artificial Neural Netw
Abstract. In this paper, we will address the endeavors of three disciplines, Psychology, Neuroscience, and Artificial Neural Network (ANN) modeling, in explaining how the mind perc...
Etienne B. Roesch, David Sander, Klaus R. Scherer