I would like to impose constraints during the training phase of a neural network. In other words, in addition to providing the inputs and target data, I would also specify, for example, that the derivative of the neural network's outputs with respect to a certain input variable should always be positive.
MATLAB: Is it possible to impose constraints on a neural network using Neural Network Toolbox
Deep Learning Toolbox
Related Question
- Neural Network optimization using Genetic Algorithm
- Training Time delay Neural Network (tdnn) using Adam optimizer
- How to pass the performance parameters to the own custom performance function in the Neural Network Toolbox
- Does train function return neural network with the weights of last epoch or the weights of the model with the smallest loss of all epochs
Best Answer