TY - GEN
T1 - Visual learning with cellular neural networks
AU - Badalov, Alexey
AU - Vilasís-Cardona, Xavier
AU - Albo-Canals, Jordi
PY - 2012
Y1 - 2012
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84870737496&partnerID=8YFLogxK
U2 - 10.1109/CNNA.2012.6331425
DO - 10.1109/CNNA.2012.6331425
M3 - Conference contribution
AN - SCOPUS:84870737496
SN - 9781467302890
T3 - International Workshop on Cellular Nanoscale Networks and their Applications
BT - 2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012
T2 - 2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012
Y2 - 29 August 2012 through 29 August 2012
ER -