Sciweavers

259 search results - page 3 / 52
» An Exploration in the Space of Mathematical Knowledge
Sort
View
ICANN
2010
Springer
13 years 9 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...
ISM
2006
IEEE
188views Multimedia» more  ISM 2006»
13 years 8 months ago
Networked Experiments and Scientific Resource Sharing in Cooperative Knowledge Spaces
Cooperative knowledge spaces create new potentials for the experimental fields in natural sciences and engineering because they enhance the accessibility of experimental setups th...
Sabine Cikic, Sabina Jeschke, Thomas Richter, Uwe ...
MKM
2007
Springer
14 years 2 months ago
Using Formal Concept Analysis in Mathematical Discovery
Formal concept analysis (FCA) comprises a set of powerful algorithms which can be used for data analysis and manipulation, and a set of visualisation tools which enable the discove...
Simon Colton, Daniel Wagner
AIIA
2009
Springer
14 years 3 months ago
Mathematical Symbol Indexing
This paper addresses the indexing and retrieval of mathematical symbols from digitized documents. The proposed approach exploits Shape Contexts (SC) to describe the shape of mathe...
Simone Marinai, Beatrice Miotti, Giovanni Soda
NN
2007
Springer
105views Neural Networks» more  NN 2007»
13 years 8 months ago
Guiding exploration by pre-existing knowledge without modifying reward
Reinforcement learning is based on exploration of the environment and receiving reward that indicates which actions taken by the agent are good and which ones are bad. In many app...
Kary Främling