Show Reference: "A Unified Model of the Joint Development of Disparity Selectivity and Vergence Control"

A Unified Model of the Joint Development of Disparity Selectivity and Vergence Control In 2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL) (November 2012), pp. 1-6, doi:10.1109/devlrn.2012.6400876 by Yu Zhao, Constantin A. Rothkopf, Jochen Triesch, Bertram E. Shi
@inproceedings{zhao-et-al-2012,
    author = {Zhao, Yu and Rothkopf, Constantin A. and Triesch, Jochen and Shi, Bertram E.},
    booktitle = {2012 IEEE International Conference on Development and Learning and Epigenetic Robotics (ICDL)},
    doi = {10.1109/devlrn.2012.6400876},
    isbn = {978-1-4673-4965-9},
    keywords = {embodiment, eye-movements, learning, motor},
    location = {San Diego, CA, USA},
    month = nov,
    pages = {1--6},
    posted-at = {2013-06-07 16:47:55},
    priority = {2},
    publisher = {IEEE},
    title = {A Unified Model of the Joint Development of Disparity Selectivity and Vergence Control},
    url = {http://dx.doi.org/10.1109/devlrn.2012.6400876},
    year = {2012}
}

See the CiteULike entry for more info, PDF links, BibTex etc.

Zhao et al. propose a model which develops perception and behavior in parallel.

Their motivation is the embodiment idea stating that perception and behavior develop in behaving animals

Disparity-selective cells in visual cortical neurons have preferred disparities of only a few degrees whereas disparity in natural environments ranges over tens of degrees.

The possible explanation offered by Zhao et al. assumes that animals actively keep disparity within a small range, during development, and therefore only selectivity for small disparity develops.

Zhao et al. present a model of joint development of disparity selectivity and vergence control.

Zhao et al.'s model develops both disparity selection and vergence control in an effort to minimize reconstruction error.

It uses a form of sparse-coding to learn to approximate its input and a variation of the actor-critic learning algorithm called natural actor critic reinforcement learning algorithm (NACREL).

The teaching signal to the NACREL algorithm is the reconstruction error of the model after the action produced by it.