Binocular disparity encoding cells generated through an Infomax based learning algorithm

@article{Okajima2004BinocularDE,
  title={Binocular disparity encoding cells generated through an Infomax based learning algorithm},
  author={Kenji Okajima},
  journal={Neural networks : the official journal of the International Neural Network Society},
  year={2004},
  volume={17 7},
  pages={
          953-62
        }
}
A learning algorithm for a model binocular cell was derived according to an information maximization principle and by using a low signal-to-noise-ratio approximation. The algorithm updates cell's synaptic weights so that the information obtained from the cell's output is increased. According to the algorithm, model binocular cells were trained by using computer-generated stereo images as training data. As a result, cells tuned to various disparities were generated. Also, generated synaptic… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 14 CITATIONS

Distribution of independent components of binocular natural images.

  • Journal of vision
  • 2015
VIEW 8 EXCERPTS
CITES RESULTS, METHODS & BACKGROUND
HIGHLY INFLUENCED

Dictionary Learning for Stereo Image Representation

  • IEEE Transactions on Image Processing
  • 2011
VIEW 1 EXCERPT
CITES BACKGROUND

Learning of Stereo Visual Dictionaries

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND