Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networks.
Mathew Mithra NoelArunkumar LAdvait TrivediPraneet DuttaPublished in: CoRR (2021)
Keyphrases
- activation function
- convolutional neural networks
- feed forward neural networks
- feedforward neural networks
- hidden layer
- output layer
- sigmoid function
- backpropagation algorithm
- neural network
- training phase
- single hidden layer
- recurrent neural networks
- basis functions
- hidden nodes
- learning rate
- back propagation
- feed forward
- multi layer perceptron
- artificial neural networks
- training algorithm
- multilayer perceptron
- extreme learning machine
- training set
- autoregressive
- parametric models
- imprecise data
- small number
- feature vectors