Sunday, September 9, 2007

Neocognitron

  • The neocognitron, proposed by Fukushima (1980), is a hierarchical multi layered neural network capable of robust visual pattern recognition through learning.
  • The lowest stage is the input layer consisting of two-dimensional array of cells, which correspond to photo receptors of the retina.
  • The retina is a multi-layered sensory tissue that lines the back of the eye.
  • It contains millions of photoreceptors that capture light rays and convert them into electrical impulses. These impulses travel along the optic nerve to the brain where they are turned into images.
  • There are two types of photoreceptors in the retina: rods and cones. The retina contains approximately 6 million cones. The cones are contained in the macula, the portion of the retina responsible for central vision
  • Cones function best in bright light and allow us to appreciate color.
  • There are approximately 125 million rods. They are spread throughout the peripheral retina and function best in dim lighting.
  • The rods are responsible for peripheral and night vision.

No comments: