Learning Saccadic Eye Movements Using Multiscale Spatial Filters

Abstract

We describe a framework for learning saccadic eye movements using a photometric representation of target points in natural scenes. The rep(cid:173) resentation takes the form of a high-dimensional vector comprised of the responses of spatial filters at different orientations and scales. We first demonstrate the use of this response vector in the task of locating pre(cid:173) viously foveated points in a scene and subsequently use this property in a multisaccade strategy to derive an adaptive motor map for delivering accurate saccades.

Cite

Text

Rao and Ballard. "Learning Saccadic Eye Movements Using Multiscale Spatial Filters." Neural Information Processing Systems, 1994.

Markdown

[Rao and Ballard. "Learning Saccadic Eye Movements Using Multiscale Spatial Filters." Neural Information Processing Systems, 1994.](https://mlanthology.org/neurips/1994/rao1994neurips-learning/)

BibTeX

@inproceedings{rao1994neurips-learning,
  title     = {{Learning Saccadic Eye Movements Using Multiscale Spatial Filters}},
  author    = {Rao, Rajesh P. N. and Ballard, Dana H.},
  booktitle = {Neural Information Processing Systems},
  year      = {1994},
  pages     = {893-900},
  url       = {https://mlanthology.org/neurips/1994/rao1994neurips-learning/}
}