Linearization of ReLU Activation Function for Neural Network-Embedded Optimization: Optimal Day-Ahead Energy Scheduling.
Cunzhi ZhaoXingpeng LiPublished in: CoRR (2023)
Keyphrases
- activation function
- neural network
- hidden layer
- feed forward neural networks
- back propagation
- feed forward
- artificial neural networks
- neural nets
- sigmoid function
- single hidden layer
- multilayer perceptron
- learning rate
- feedforward neural networks
- hidden neurons
- radial basis function
- pattern recognition
- basis functions
- dynamic programming
- backpropagation algorithm
- stochastic programming
- network architecture
- small number
- single layer
- training algorithm
- optimization algorithm
- training phase
- multi layer perceptron
- optimal solution
- feature selection
- multi layer
- input space
- fuzzy logic
- optimization method
- genetic algorithm