Using Bottlenecks in Feedforward Networks as a Dimension Reduction Technique: An Application to Optimization Tasks

Wiles, Janet; Bakker, Paul; Lynton, Adam; Norris, Michael; Parkinson, Sean; Staples, Mark; Whiteside, Alan

doi:10.1162/neco.1996.8.6.1179

Cited by 1 publication

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The advantage of using a neural network for NLDR is that it can learn directly from training examples (such as human prelabeled data) to form a model of the feature data. The basis for NLDR is the standard non-linear regression analysis used in the neural network approach, which has been widely studied [9], [13], [33]. Through training, the distance information of the original data source can be represented as weights between units in successive layers of the neural network.…”

Section: B Dimension Reduction Methodsmentioning

confidence: 99%

Towards Effective Content-Based Music Retrieval With Multiple Acoustic Feature Combination

Shen

Shepherd

Ngu

2006

IEEE Trans. Multimedia

View full text Add to dashboard Cite

In this paper, we present a new approach to constructing music descriptors to support efficient content-based music retrieval and classification. The system applies multiple musical properties combined with a hybrid architecture based on principal component analysis (PCA) and a multilayer perceptron neural network. This architecture enables straightforward incorporation of multiple musical feature vectors, based on properties such as timbral texture, pitch, and rhythm structure, into a single low-dimensioned vector that is more effective for classification than the larger individual feature vectors. The use of supervised training enables incorporation of human musical perception that further enhances the classification process. We compare our approach with state of the art techniques and demonstrate its effectiveness on content-based music retrieval. In addition, extensive experimental study illustrates its effectiveness and robustness against various kinds of audio alteration.

show abstract

Section: B Dimension Reduction Methodsmentioning

confidence: 99%