Title :
When a feature detector becomes a feature generator
Author :
Micheli-Tzanakou, E.
Author_Institution :
Dept. of Biomedical Eng., Rutgers Univ., New Brunswick, NJ, USA
Abstract :
The neural network approach is reviewed in the context of studies in the animal and human visual systems. An attempt is made to explain perception, memory, and learning as a feedback loop similar to the one used in the ALOPEX optimization concept. Applications in pattern recognition and image processing are discussed. Experiments using visual evoked potentials in humans are described.<>
Keywords :
neural nets; pattern recognition; physiological models; picture processing; visual perception; ALOPEX optimization concept; animal visual systems; feature detector; feature generator; feedback loop; human visual systems; image processing; learning; memory; neural network approach; pattern recognition; perception; visual evoked potentials; Animals; Biomedical measurements; Computer vision; Cost function; Detectors; Feedback loop; Humans; Neurons; Optimization methods; Temperature;
Journal_Title :
Engineering in Medicine and Biology Magazine, IEEE
