An Empirically-Sourced Heuristic for Predetermining the Size of the Hidden Layer of a Multi-layer Perceptron for Large Datasets.
Amanda LuntShuxiang XuPublished in: Australasian Conference on Artificial Intelligence (2016)
Keyphrases
- hidden layer
- back propagation
- recurrent neural networks
- learning rate
- neural network
- feed forward
- feed forward neural networks
- multilayer perceptron
- feedforward neural networks
- artificial neural networks
- activation function
- radial basis function
- rbf neural network
- neural nets
- number of hidden layers
- output layer
- dynamic programming
- optimal solution
- feature selection
- simulated annealing
- control system
- training set
- pattern recognition
- hidden units