Feature selection using Deep Neural Networks

Ray, Debjyoti and Kodukula, Sri Rama Murty and C, Krishna Mohan (2015) Feature selection using Deep Neural Networks. In: International Joint Conference on Neural Networks (IJCNN), 12-17 July, 2015, Killarney.

Feature Selection using Deep Neural Networks.pdf - Accepted Version

Download (731kB) | Preview


Feature descriptors involved in video processing are generally high dimensional in nature. Even though the extracted features are high dimensional, many a times the task at hand depends only on a small subset of these features. For example, if two actions like running and walking have to be identified, extracting features related to the leg movement of the person is enough. Since, this subset is not known apriori, we tend to use all the features, irrespective of the complexity of the task at hand. Selecting task-aware features may not only improve the efficiency but also the accuracy of the system. In this work, we propose a supervised approach for task-aware selection of features using Deep Neural Networks (DNN) in the context of action recognition. The activation potentials contributed by each of the individual input dimensions at the first hidden layer are used for selecting the most appropriate features. The selected features are found to give better classification performance than the original high-dimensional features. It is also shown that the classification performance of the proposed feature selection technique is superior to the low-dimensional representation obtained by principal component analysis (PCA).

[error in script]
IITH Creators:
IITH CreatorsORCiD
Kodukula, Sri Rama Murtyhttps://orcid.org/0000-0002-6355-5287
Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: Action Recognition Deep Neural Networks Supervised Feature Selection
Subjects: Others > Electricity
Divisions: Department of Computer Science & Engineering
Department of Electrical Engineering
Depositing User: Team Library
Date Deposited: 08 Jan 2016 09:46
Last Modified: 15 Jun 2018 06:33
URI: http://raiith.iith.ac.in/id/eprint/2108
Publisher URL: https://doi.org/10.1109/IJCNN.2015.7280626
Related URLs:

Actions (login required)

View Item View Item
Statistics for RAIITH ePrint 2108 Statistics for this ePrint Item