Sciweavers

1701 search results - page 165 / 341
» Learning Mappings with Neural Network
Sort
View
NN
2002
Springer
113views Neural Networks» more  NN 2002»
15 years 5 months ago
Control of exploitation-exploration meta-parameter in reinforcement learning
In reinforcement learning (RL), the duality between exploitation and exploration has long been an important issue. This paper presents a new method that controls the balance betwe...
Shin Ishii, Wako Yoshida, Junichiro Yoshimoto
ICANN
2010
Springer
15 years 4 months ago
Dynamic Shape Learning and Forgetting
In this paper, we present a system capable of dynamically learning shapes in a way that also allows for the dynamic deletion of shapes already learned. It uses a self-balancing Bin...
Nikolaos Tsapanos, Anastasios Tefas, Ioannis Pitas
ICANN
2011
Springer
14 years 9 months ago
Learning from Multiple Annotators with Gaussian Processes
Abstract. In many supervised learning tasks it can be costly or infeasible to obtain objective, reliable labels. We may, however, be able to obtain a large number of subjective, po...
Perry Groot, Adriana Birlutiu, Tom Heskes
IJCNN
2000
IEEE
15 years 10 months ago
Metrics that Learn Relevance
We introduce an algorithm for learning a local metric to a continuous input space that measures distances in terms of relevance to the processing task. The relevance is defined a...
Samuel Kaski, Janne Sinkkonen
SBRN
2008
IEEE
16 years 19 days ago
Using a Probabilistic Neural Network for a Large Multi-label Problem
The automation of the categorization of economic activities from business descriptions in free text format is a huge challenge for the Brazilian governmental administration in the...
Elias Oliveira, Patrick Marques Ciarelli, Alberto ...