Sciweavers

ESANN
2008
13 years 11 months ago
Safe exploration for reinforcement learning
In this paper we define and address the problem of safe exploration in the context of reinforcement learning. Our notion of safety is concerned with states or transitions that can ...
Alexander Hans, Daniel Schneegaß, Anton Maxi...
ESANN
2008
13 years 11 months ago
A Method for Time Series Prediction using a Combination of Linear Models
This paper presents a new approach for time series prediction using local dynamic modeling. The proposed method is composed of three blocks: a Time Delay Line that transforms the o...
David Martínez-Rego, Oscar Fontenla-Romero,...
ESANN
2008
13 years 11 months ago
Robust object segmentation by adaptive metrics in Generalized LVQ
We investigate the effect of several adaptive metrics in the context of figure-ground segregation, using Generalized LVQ to train a classifier for image regions. Extending the Euc...
Alexander Denecke, Heiko Wersing, Jochen J. Steil,...
ESANN
2008
13 years 11 months ago
Improvement in Game Agent Control Using State-Action Value Scaling
The aim of this paper is to enhance the performance of a reinforcement learning game agent controller, within a dynamic game environment, through the retention of learned informati...
Leo Galway, Darryl Charles, Michaela M. Black
ESANN
2008
13 years 11 months ago
Machine learning in cancer research: implications for personalised medicine
Driven by the growing demand of personalization of medical procedures, data-based, computer-aided cancer research in human patients is advancing at an accelerating pace, providing ...
Alfredo Vellido, Elia Biganzoli, Paulo J. G. Lisbo...
ESANN
2008
13 years 11 months ago
Active and reactive use of virtual neural sensors
This paper addresses the possible use of virtual neural sensors, implemented by means of weightless systems, as active or reactive sensors. The latter, made possible by the intrins...
Massimo De Gregorio
ESANN
2008
13 years 11 months ago
Neuromimetic motion indicator for visual perception
This paper presents a bio-inspired model for visual perception of motion through its principal indicator : the neuromimetic motion indicator (NMI). This indicator emerges out of th...
Claudio Castellanos Sánchez
ESANN
2008
13 years 11 months ago
A multiple testing procedure for input variable selection in neural networks
In this paper a novel procedure to select the input nodes in neural network modeling is presented and discussed. The approach is developed in a multiple testing framework and so it...
Michele La Rocca, Cira Perna
ESANN
2008
13 years 11 months ago
Similarities and differences between policy gradient methods and evolution strategies
Natural policy gradient methods and the covariance matrix adaptation evolution strategy, two variable metric methods proposed for solving reinforcement learning tasks, are contrast...
Verena Heidrich-Meisner, Christian Igel
ESANN
2008
13 years 11 months ago
The impact of axon wiring costs on small neuronal networks
Recent papers by D. Chklovskii and E.M. Izhikevich suggest that wiring costs may play a significant role in the physical layout and function of neuronal structures. About eighty ye...
Conrad Attard, Andreas Alexander Albrecht