Sciweavers

Share
ICANN
2011
Springer
2 years 7 months ago
Learning Curves for Gaussian Processes via Numerical Cubature Integration
This paper is concerned with estimation of learning curves for Gaussian process regression with multidimensional numerical integration. We propose an approach where the recursion e...
Simo Särkkä
ICANN
2011
Springer
2 years 7 months ago
Transforming Auto-Encoders
The artificial neural networks that are used to recognize shapes typically use one or more layers of learned feature detectors that produce scalar outputs. By contrast, the comput...
Geoffrey E. Hinton, Alex Krizhevsky, Sida D. Wang
ICANN
2011
Springer
2 years 7 months ago
Semi-supervised Learning for WLAN Positioning
Currently the most accurate WLAN positioning systems are based on the fingerprinting approach, where a “radio map” is constructed by modeling how the signal strength measureme...
Teemu Pulkkinen, Teemu Roos, Petri Myllymäki
ICANN
2011
Springer
2 years 7 months ago
Extending Tree Kernels with Topological Information
The definition of appropriate kernel functions is crucial for the performance of a kernel method. In many of the state-of-the-art kernels for trees, matching substructures are con...
Fabio Aiolli, Giovanni Da San Martino, Alessandro ...
ICANN
2011
Springer
2 years 7 months ago
Cross-Species Translation of Multi-way Biomarkers
Abstract. We present a Bayesian translational model for matching patterns in data sets which have neither co-occurring samples nor variables, but only a similar experiment design d...
Tommi Suvitaival, Ilkka Huopaniemi, Matej Oresic, ...
ICANN
2011
Springer
2 years 7 months ago
Automatic Seizure Detection Incorporating Structural Information
Abstract. Traditional seizure detection algorithms act on single channels ignoring the synchronously recorded, inherently interdependent multichannel nature of EEG. However, the sp...
Borbala Hunyadi, Maarten De Vos, Marco Signoretto,...
ICASSP
2011
IEEE
2 years 7 months ago
Deep neural networks for acoustic emotion recognition: Raising the benchmarks
Deep Neural Networks (DNNs) denote multilayer artificial neural networks with more than one hidden layer and millions of free parameters. We propose a Generalized Discriminant An...
André Stuhlsatz, Christine Meyer, Florian E...
ICASSP
2011
IEEE
2 years 8 months ago
Arccosine kernels: Acoustic modeling with infinite neural networks
Neural networks are a useful alternative to Gaussian mixture models for acoustic modeling; however, training multilayer networks involves a difficult, nonconvex optimization that...
Chih-Chieh Cheng, Brian Kingsbury
OL
2011
184views Neural Networks» more  OL 2011»
2 years 10 months ago
Privacy-preserving linear programming
Abstract. We propose a privacy-preserving formulation of a linear program whose constraint matrix is partitioned into groups of columns where each group of columns and its correspo...
O. L. Mangasarian
SPIC
2010
2 years 11 months ago
Attention-based video streaming
This paper presents a complete framework for attention-based video streaming for low bandwidth networks. First, motivated by the fovea-periphery distinction of biological vision s...
Çagatay Dikici, H. Isil Bozma
books