Self-Organizing Neural Population Coding for improving robotic visuomotor coordination In Neural Networks (IJCNN), The 2011 International Joint Conference on (July 2011), pp. 1437-1444, doi:10.1109/ijcnn.2011.6033393 by Tao Zhou, Piotr Dudek, Bertram E. Shi

@inproceedings{zhou-et-al-2011, abstract = {We present an extension of Kohonen's Self Organizing Map ({SOM}) algorithm called the Self Organizing Neural Population Coding ({SONPC}) algorithm. The algorithm adapts online the neural population encoding of sensory and motor coordinates of a robot according to the underlying data distribution. By allocating more neurons towards area of sensory or motor space which are more frequently visited, this representation improves the accuracy of a robot system on a visually guided reaching task. We also suggest a Mean Reflection method to solve the notorious border effect problem encountered with {SOMs} for the special case where the latent space and the data space dimensions are the same.}, author = {Zhou, Tao and Dudek, Piotr and Shi, Bertram E.}, booktitle = {Neural Networks (IJCNN), The 2011 International Joint Conference on}, doi = {10.1109/ijcnn.2011.6033393}, institution = {Dept. of Electron. \& Comput. Eng., Hong Kong Univ. of Sci. \& Technol., Kowloon, China}, isbn = {978-1-4244-9635-8}, issn = {2161-4393}, keywords = {learning, population-coding, som}, month = jul, pages = {1437--1444}, posted-at = {2013-02-11 10:13:02}, priority = {2}, publisher = {IEEE}, title = {{Self-Organizing} Neural Population Coding for improving robotic visuomotor coordination}, url = {http://dx.doi.org/10.1109/ijcnn.2011.6033393}, year = {2011} }

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

The SOM can be modified to take into account the variance of the input dimensions wrt. each other.⇒

Zhou et al. use an approach similar to that of Bauer et al.
They do not use *pairwise cross-correlation* between input modalities, but simply *variances* of individual modalities.
It is unclear how they handle the case where one modality essentially becomes ground truth to the algorithm.⇒

A SOM models a population and each unit has a response to a stimulus; it is therefore possible to read out a population code from a SOM. This population code is not very meaningful in the standard SOM. Given a more statistically motivated distance function, the population code can be made more meaningful.⇒

Zhou et al.'s and Bauer et al.'s statistical SOM variants assume Gaussian noise in the input.⇒