Title :
Application of Hopfield network to saccades
Author :
Washizawa, Teruyoshi
Author_Institution :
Fac. of Letters, Keio Univ., Kanagawa, Japan
fDate :
11/1/1993 12:00:00 AM
Abstract :
Human eye movement mechanisms (saccades) are very useful for scene analysis, including object representation and pattern recognition. A Hopfield neural network for emulating saccades is proposed. The network uses an energy function that includes location and identification tasks. Computer simulation shows that the network performs those tasks cooperatively. The result suggests that the network is applicable to shift-invariant pattern recognition
Keywords :
Hopfield neural nets; computer vision; digital simulation; eye; image recognition; physiological models; vision; Hopfield neural network; computer simulation; human eye movement mechanisms; identification; location; object representation; saccades; scene analysis; shift-invariant pattern recognition; Acoustic signal processing; Artificial neural networks; Automation; Feature extraction; Neural networks; Pattern recognition; Probability distribution; Testing; Training data; Underwater acoustics;
Journal_Title :
Neural Networks, IEEE Transactions on
