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
Text
Hartono et al. "Classifier with Hierarchical Topographical Maps as Internal Representation." International Conference on Learning Representations, 2015. doi:10.1109/INES.2015.7329752Markdown
[Hartono et al. "Classifier with Hierarchical Topographical Maps as Internal Representation." International Conference on Learning Representations, 2015.](https://mlanthology.org/iclr/2015/hartono2015iclr-classifier/) doi:10.1109/INES.2015.7329752BibTeX
@inproceedings{hartono2015iclr-classifier,
title = {{Classifier with Hierarchical Topographical Maps as Internal Representation}},
author = {Hartono, Pitoyo and Hollensen, Paul and Trappenberg, Thomas},
booktitle = {International Conference on Learning Representations},
year = {2015},
doi = {10.1109/INES.2015.7329752},
url = {https://mlanthology.org/iclr/2015/hartono2015iclr-classifier/}
}