Learning continuous piecewise non-linear activation functions for deep neural networks.
Xinchen GaoYawei LiWen LiLixin DuanLuc Van GoolLuca BeniniMichele MagnoPublished in: ICME (2023)
Keyphrases
- neural network
- activation function
- feedforward neural networks
- neural nets
- learning speed
- learning algorithm
- feed forward
- supervised learning
- learning process
- artificial neural networks
- back propagation
- learning tasks
- dynamic programming
- prior knowledge
- feature space
- pattern recognition
- multi layer
- reinforcement learning
- feed forward neural networks
- training data
- feature selection