Distinction between features extracted using deep belief networks
This work tackles feature selection in machine learning, but appears incremental as it builds on existing methods like DBNs without introducing a new paradigm.
The paper addresses the problem of irrelevant features in automated feature extraction by proposing two methods to distinguish features based on their relevance to a specific task, applied to a Deep Belief Network for face recognition.
Data representation is an important pre-processing step in many machine learning algorithms. There are a number of methods used for this task such as Deep Belief Networks (DBNs) and Discrete Fourier Transforms (DFTs). Since some of the features extracted using automated feature extraction methods may not always be related to a specific machine learning task, in this paper we propose two methods in order to make a distinction between extracted features based on their relevancy to the task. We applied these two methods to a Deep Belief Network trained for a face recognition task.