Visual learning with cellular neural networks

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

doi:10.1109/CNNA.2012.6331425

Visual learning with cellular neural networks

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

^*Corresponding author for this work

La Salle International School of Commerce and Digital Economy

Research output: Book chapter › Conference contribution › peer-review

Abstract

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.

Original language	English
Title of host publication	2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012
DOIs	https://doi.org/10.1109/CNNA.2012.6331425
Publication status	Published - 2012
Event	2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012 - Turin, Italy Duration: 29 Aug 2012 → 29 Aug 2012

Publication series

Name	International Workshop on Cellular Nanoscale Networks and their Applications
ISSN (Print)	2165-0160
ISSN (Electronic)	2165-0179

Conference

Conference	2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012
Country/Territory	Italy
City	Turin
Period	29/08/12 → 29/08/12

Access to Document

10.1109/CNNA.2012.6331425

Cite this

@inproceedings{67411cbe4ebd4defbecd9737a8267917,

title = "Visual learning with cellular neural networks",

abstract = "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.",

author = "Alexey Badalov and Xavier Vilas{\'i}s-Cardona and Jordi Albo-Canals",

year = "2012",

doi = "10.1109/CNNA.2012.6331425",

language = "English",

isbn = "9781467302890",

series = "International Workshop on Cellular Nanoscale Networks and their Applications",

booktitle = "2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012",

note = "2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012 ; Conference date: 29-08-2012 Through 29-08-2012",

}

Badalov, A, Vilasís-Cardona, X & Albo-Canals, J 2012, Visual learning with cellular neural networks. in 2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012., 6331425, International Workshop on Cellular Nanoscale Networks and their Applications, 2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012, Turin, Italy, 29/08/12. https://doi.org/10.1109/CNNA.2012.6331425

Visual learning with cellular neural networks. / Badalov, Alexey; Vilasís-Cardona, Xavier; Albo-Canals, Jordi.
2012 13th International Workshop on Cellular Nanoscale Networks and their Applications, CNNA 2012. 2012. 6331425 (International Workshop on Cellular Nanoscale Networks and their Applications).

Research output: Book chapter › Conference contribution › peer-review

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 - https://www.scopus.com/pages/publications/84870737496

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 -

Visual learning with cellular neural networks

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this