Discriminative Autoencoder for Feature Extraction: Application to Character Recognition

Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to variations commonly encountered in image datasets. Using the basic...

Full description

Saved in:
Bibliographic Details
Published in:Neural processing letters 2019-06, Vol.49 (3), p.1723-1735
Main Authors: Gogna, Anupriya, Majumdar, Angshul
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Automation
Belief networks
Character recognition
Classification
Complex Systems
Computational Intelligence
Computer Science
Datasets
Deep learning
Dictionaries
Feature extraction
Machine learning
Representations
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Conventionally, autoencoders are unsupervised representation learning tools. In this work, we propose a novel discriminative autoencoder. Use of supervised discriminative learning ensures that the learned representation is robust to variations commonly encountered in image datasets. Using the basic discriminating autoencoder as a unit, we build a stacked architecture aimed at extracting relevant representation from the training data. The efficiency of our feature extraction algorithm ensures a high classification accuracy with even simple classification schemes like KNN (K-nearest neighbor). We demonstrate the superiority of our model for representation learning by conducting experiments on standard datasets for character/image recognition and subsequent comparison with existing supervised deep architectures like class sparse stacked autoencoder and discriminative deep belief network.
ISSN:1370-4621
1573-773X
DOI:10.1007/s11063-018-9894-5