Using Bottlenecks in Feedforward Networks as a Dimension Reduction Technique: An Application to Optimization Tasks.
Janet WilesPaul BakkerAdam LyntonMichael NorrisSean ParkinsonMark StaplesAlan WhitesidePublished in: Neural Comput. (1996)
Keyphrases
- dimension reduction
- feed forward
- recurrent networks
- principal component analysis
- feature extraction
- artificial neural networks
- back propagation
- neural nets
- high dimensional problems
- singular value decomposition
- neural network
- visual cortex
- cluster analysis
- high dimensional data
- low dimensional
- manifold learning
- recurrent neural networks
- high dimensionality
- high dimensional
- biologically plausible
- random projections
- spiking neurons
- high dimensional data analysis
- hidden layer
- dimensionality reduction
- feature space
- adaptive neural
- dimension reduction methods
- multi task
- linear discriminant analysis
- artificial intelligence