Sciweavers

ICANN
2007
Springer
14 years 5 months ago
Some Properties of the Gaussian Kernel for One Class Learning
This paper proposes a novel approach for directly tuning the gaussian kernel matrix for one class learning. The popular gaussian kernel includes a free parameter, σ, that requires...
Paul F. Evangelista, Mark J. Embrechts, Boleslaw K...
ICANN
2007
Springer
14 years 5 months ago
Evolutionary Multi-objective Optimization of Spiking Neural Networks
Evolutionary multi-objective optimization of spiking neural networks for solving classification problems is studied in this paper. By means of a Paretobased multi-objective geneti...
Yaochu Jin, Ruojing Wen, Bernhard Sendhoff
ICANN
2007
Springer
14 years 5 months ago
Generalized Softmax Networks for Non-linear Component Extraction
Abstract. We develop a probabilistic interpretation of non-linear component extraction in neural networks that activate their hidden units according to a softmaxlike mechanism. On ...
Jörg Lücke, Maneesh Sahani
ICANN
2007
Springer
14 years 5 months ago
SpikeStream: A Fast and Flexible Simulator of Spiking Neural Networks
SpikeStream is a new simulator of biologically structured spiking neural networks that can be used to edit, display and simulate up to 100,000 neurons. This simulator uses a combin...
David Gamez
ICANN
2007
Springer
14 years 5 months ago
Incremental One-Class Learning with Bounded Computational Complexity
Rowland R. Sillito, Robert B. Fisher
ICANN
2007
Springer
14 years 5 months ago
A Marker-Based Model for the Ontogenesis of Routing Circuits
Abstract. We present a model for the ontogenesis of information routing architectures in the brain based on chemical markers guiding axon growth. The model produces all-to-all conn...
Philipp Wolfrum, Christoph von der Malsburg
ICANN
2007
Springer
14 years 5 months ago
Sparse and Transformation-Invariant Hierarchical NMF
The hierarchical non-negative matrix factorization (HNMF) is a multilayer generative network for decomposing strictly positive data into strictly positive activations and base vect...
Sven Rebhan, Julian Eggert, Horst-Michael Gro&szli...
ICANN
2007
Springer
14 years 5 months ago
Structure Learning with Nonparametric Decomposable Models
Abstract. We present a novel approach to structure learning for graphical models. By using nonparametric estimates to model clique densities in decomposable models, both discrete a...
Anton Schwaighofer, Mathäus Dejori, Volker Tr...
ICANN
2007
Springer
14 years 5 months ago
Deformable Radial Basis Functions
Radial basis function networks (RBF) are efficient general function approximators. They show good generalization performance and they are easy to train. Due to theoretical consider...
Wolfgang Hübner, Hanspeter A. Mallot
ICANN
2007
Springer
14 years 5 months ago
Incremental and Decremental Learning for Linear Support Vector Machines
Abstract. We present a method to find the exact maximal margin hyperplane for linear Support Vector Machines when a new (existing) component is added (removed) to (from) the inner...
Enrique Romero, Ignacio Barrio, Lluís Belan...