Can I read Auto-clustering Output Layer: Automatic Learning of Latent Annotations in Neural Networks on EtoBox?

Auto-clustering Output Layer: Automatic Learning of Latent Annotations in Neural Networks by Kilinc, Ozsel; Uysal, Ismail is a scholarly article available to read on EtoBox.

What is Auto-clustering Output Layer: Automatic Learning of Latent Annotations in Neural Networks about?

In this paper, we discuss a different type of semi-supervised setting: a coarse level of labeling is available for all observations but the model has to learn a fine level of latent annotation for each one of them. Problems in this setting are likely to be encountered in many domains such as text categorization, protein function prediction, image classification as well as in exploratory scientific studies such as medical and genomics research. We consider this setting as simultaneously performed supervised classification (per the available coarse labels) and unsupervised clustering (within each one of the coarse labels) and propose a novel output layer modification called auto-clustering output layer (ACOL) that allows concurrent classification and clustering based on Graph-based Activity Regularization (GAR) technique. As the proposed output layer modification duplicates the softmax nodes at the output layer for each class, GAR allows for competitive learning between these duplicates on a traditional error-correction learning framework to ultimately enable a neural network to learn the latent annotations in this partially supervised setup. We demonstrate how the coarse label super

Author

Kilinc, Ozsel; Uysal, Ismail

Published

2017

Language

EN