DeepAI AI Chat
Log In Sign Up

Unsupervised Feature Learning through Divergent Discriminative Feature Accumulation

by   Paul A. Szerlip, et al.
University of Central Florida

Unlike unsupervised approaches such as autoencoders that learn to reconstruct their inputs, this paper introduces an alternative approach to unsupervised feature learning called divergent discriminative feature accumulation (DDFA) that instead continually accumulates features that make novel discriminations among the training set. Thus DDFA features are inherently discriminative from the start even though they are trained without knowledge of the ultimate classification problem. Interestingly, DDFA also continues to add new features indefinitely (so it does not depend on a hidden layer size), is not based on minimizing error, and is inherently divergent instead of convergent, thereby providing a unique direction of research for unsupervised feature learning. In this paper the quality of its learned features is demonstrated on the MNIST dataset, where its performance confirms that indeed DDFA is a viable technique for learning useful features.


page 1

page 2

page 3

page 4


A Theory of Feature Learning

Feature Learning aims to extract relevant information contained in data ...

Full-info Training for Deep Speaker Feature Learning

In recent studies, it has shown that speaker patterns can be learned fro...

EE-AE: An Exclusivity Enhanced Unsupervised Feature Learning Approach

Unsupervised learning is becoming more and more important recently. As o...

Learning Discriminative Features using Encoder-Decoder type Deep Neural Nets

As machine learning is applied to an increasing variety of complex probl...

Parametric Instance Classification for Unsupervised Visual Feature Learning

This paper presents parametric instance classification (PIC) for unsuper...

Role of zero synapses in unsupervised feature learning

Synapses in real neural circuits can take discrete values, including zer...

Unsupervised Feature Learning for Audio Analysis

Identifying acoustic events from a continuously streaming audio source i...