Principal Components Identify MLP Hidden Layer Size for Optimal Generalisation Performance.
Mark GirolamiPublished in: ICANNGA (1997)
Keyphrases
- principal components
- hidden layer
- multilayer perceptron
- back propagation
- activation function
- neural network
- radial basis function
- artificial neural networks
- principal component analysis
- feed forward
- hidden nodes
- learning rate
- connection weights
- feed forward neural networks
- multi layer perceptron
- hidden neurons
- feedforward neural networks
- output layer
- rbf neural network
- neural network model
- dimensionality reduction
- recurrent neural networks
- optimal solution
- dynamic programming
- latent variables
- covariance matrix
- data sets
- fuzzy logic
- bayesian networks
- neural nets
- worst case
- similarity measure
- rbf network
- machine learning