Sciweavers

ICANN
2010
Springer
13 years 11 months ago
On Estimating Mutual Information for Feature Selection
Abstract. Mutual Information (MI) is a powerful concept from information theory used in many application fields. For practical tasks it is often necessary to estimate the Mutual In...
Erik Schaffernicht, Robert Kaltenhaeuser, Saurabh ...
ICANN
2010
Springer
13 years 11 months ago
Neuro-symbolic Representation of Logic Programs Defining Infinite Sets
It has been one of the great challenges of neuro-symbolic integration to represent recursive logic programs using neural networks of finite size. In this paper, we propose to imple...
Ekaterina Komendantskaya, Krysia Broda, Artur S. d...
ICANN
2010
Springer
13 years 11 months ago
Kernel-Based Learning from Infinite Dimensional 2-Way Tensors
Abstract. In this paper we elaborate on a kernel extension to tensorbased data analysis. The proposed ideas find applications in supervised learning problems where input data have ...
Marco Signoretto, Lieven De Lathauwer, Johan A. K....
ICANN
2010
Springer
13 years 11 months ago
Action Classification in Soccer Videos with Long Short-Term Memory Recurrent Neural Networks
Abstract. In this paper, we propose a novel approach for action classification in soccer videos using a recurrent neural network scheme. Thereby, we extract from each video action ...
Moez Baccouche, Franck Mamalet, Christian Wolf, Ch...
ICANN
2010
Springer
13 years 11 months ago
Visualising Clusters in Self-Organising Maps with Minimum Spanning Trees
Abstract. The Self-Organising Map (SOM) is a well-known neuralnetwork model that has successfully been used as a data analysis tool in many different domains. The SOM provides a to...
Rudolf Mayer, Andreas Rauber
ICANN
2010
Springer
13 years 11 months ago
Reinforcement Learning Based Neural Controllers for Dynamic Processes without Exploration
Abstract. In this paper we present a Reinforcement Learning (RL) approach with the capability to train neural adaptive controllers for complex control problems without expensive on...
Frank-Florian Steege, André Hartmann, Erik ...
ICANN
2010
Springer
13 years 11 months ago
Using Reinforcement Learning to Guide the Development of Self-organised Feature Maps for Visual Orienting
We present a biologically inspired neural network model of visual orienting (using saccadic eye movements) in which targets are preferentially selected according to their reward va...
Kevin Brohan, Kevin N. Gurney, Piotr Dudek
ICANN
2010
Springer
13 years 11 months ago
Recurrence Enhances the Spatial Encoding of Static Inputs in Reservoir Networks
We shed light on the key ingredients of reservoir computing and analyze the contribution of the network dynamics to the spatial encoding of inputs. Therefore, we introduce attracto...
Christian Emmerich, René Felix Reinhart, Jo...
ICANN
2010
Springer
13 years 11 months ago
Exploring Continuous Action Spaces with Diffusion Trees for Reinforcement Learning
We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
Christian Vollmer, Erik Schaffernicht, Horst-Micha...
ICANN
2010
Springer
13 years 11 months ago
An Artificial Immune Network for Multi-objective Optimization
Aris Lanaridis, Andreas Stafylopatis