Classifier with Hierarchical Topographical Maps as Internal Representation
Abstract
In this study we want to connect our previously proposed context-relevant topographical maps with the deep learning community. Our architecture is a classifier with hidden layers that are hierarchical two-dimensional topographical maps. These maps differ from the conventional self-organizing maps in that their organizations are influenced by the context of the data labels in a top-down manner. In this way bottom-up and top-down learning are combined in a biologically relevant representational learning setting. Compared to our previous work, we are here specifically elaborating the model in a more challenging setting compared to our previous experiments and to advance more hidden representation layers to bring our discussions into the context of deep representational learning.
Cite
@article{arxiv.1412.6567,
title = {Classifier with Hierarchical Topographical Maps as Internal Representation},
author = {Thomas Trappenberg and Paul Hollensen and Pitoyo Hartono},
journal= {arXiv preprint arXiv:1412.6567},
year = {2015}
}