Empirical study of the modulus as activation function in computer vision applications.
Iván Vallés-PérezEmilio Soria-OlivasMarcelino Martínez-SoberAntonio J. Serrano-LópezJoan Vila-FrancésJuan Gómez-SanchísPublished in: Eng. Appl. Artif. Intell. (2023)
Keyphrases
- empirical studies
- activation function
- computer vision
- neural network
- feed forward
- hidden layer
- artificial neural networks
- back propagation
- feed forward neural networks
- pattern recognition
- learning rate
- neural nets
- network architecture
- empirical analysis
- sigmoid function
- basis functions
- feedforward neural networks
- chaotic neural network
- hidden nodes
- multilayer perceptron
- image segmentation
- machine learning
- radial basis function
- linear combination
- multi layer perceptron
- autoregressive
- signal processing
- optical flow
- extreme learning machine