Visual learning with cellular neural networks

Alexey Badalov, Xavier Vilasís-Cardona, Jordi Albo-Canals

Producció científica: Capítol de llibreContribució a congrés/conferènciaAvaluat per experts

Resum

Reinforcement learning is a powerful tool for teaching robotic agents to perform tasks in real environments. Visual information provided by a camera could be a cheap and rich source of information about an agent's surroundings, if this information were represented in a compact and generalizable form. We turn to cellular neural networks as the means of transforming visual input to a representation suitable for reinforcement learning. We investigate a CNN-based image processing algorithm and describe a method for efficiently computing CNNs using the DirectX 10 API.

Idioma originalAnglès
Títol de la publicació2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012
DOIs
Estat de la publicacióPublicada - 2012
Esdeveniment2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012 - Turin, Italy
Durada: 29 d’ag. 201229 d’ag. 2012

Sèrie de publicacions

NomInternational Workshop on Cellular Nanoscale Networks and their Applications
ISSN (imprès)2165-0160
ISSN (electrònic)2165-0179

Conferència

Conferència2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012
País/TerritoriItaly
CiutatTurin
Període29/08/1229/08/12

Fingerprint

Navegar pels temes de recerca de 'Visual learning with cellular neural networks'. Junts formen un fingerprint únic.

Com citar-ho