Title :
Exploitation of structured gating connections for the normalization of a visual pattern
Author :
Sperduti, Alessandro
Author_Institution :
ICSI, Berkeley, CA, USA
Abstract :
Structured gating connections can be useful for reducing the complexity of networks with a high number of inputs. An example of their application to the normalization of a visual pattern with respect to scale and position is presented. The use of gating connections allows us to have a linear number of connections in the number of pixels. The connections are also very localized.
Keywords :
edge detection; function approximation; image processing; recurrent neural nets; edge detection; function approximation; image recognition; normalization; recurrent neural networks; scale; structured gating connections; visual pattern; Cutoff frequency; Detectors; Feedforward systems; Image analysis; Image edge detection; Low pass filters; Neural networks; Neurons; Pattern recognition; Performance analysis;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.713899
