Sciweavers

ICANN
2005
Springer
13 years 10 months ago
Dynamics of Cortical Columns - Self-organization of Receptive Fields
We present a system of differential equations which abstractly models neural dynamics and synaptic plasticity of a cortical macrocolumn. The equations assume inhibitory coupling b...
Jörg Lücke, Jan D. Bouecke
ICANN
2005
Springer
13 years 10 months ago
LS-SVM Hyperparameter Selection with a Nonparametric Noise Estimator
This paper presents a new method for the selection of the two hyperparameters of Least Squares Support Vector Machine (LS-SVM) approximators with Gaussian Kernels. The two hyperpar...
Amaury Lendasse, Yongnan Ji, Nima Reyhani, Michel ...
ICANN
2005
Springer
13 years 10 months ago
Evolution of Heuristics for Give-Away Checkers
The efficacy of two evolutionary approaches to the problem of generation of heuristical linear and non-linear evaluation functions in the game of give-away checkers is tested in th...
Magdalena Kusiak, Karol Waledzik, Jacek Mandziuk
ICANN
2005
Springer
13 years 10 months ago
Online Learning for Object Recognition with a Hierarchical Visual Cortex Model
We present an architecture for the online learning of object representations based on a visual cortex hierarchy developed earlier. We use the output of a topographical feature hier...
Stephan Kirstein, Heiko Wersing, Edgar Körner
ICANN
2005
Springer
13 years 10 months ago
A Neural Network for Text Representation
Text categorization and retrieval tasks are often based on a good representation of textual data. Departing from the classical vector space model, several probabilistic models have...
Mikaela Keller, Samy Bengio
ICANN
2005
Springer
13 years 10 months ago
CrySSMEx, a Novel Rule Extractor for Recurrent Neural Networks: Overview and Case Study
In this paper, it will be shown that it is feasible to extract finite state machines in a domain of, for rule extraction, previously unencountered complexity. The algorithm used i...
Henrik Jacobsson, Tom Ziemke
ICANN
2005
Springer
13 years 10 months ago
Combining Attention and Value Maps
We present an approach where we combine attention with value maps for the purpose of acquiring a decision-making policy for multiple concurrent goals. The former component is essen...
Stathis Kasderidis, John G. Taylor