I want to design a neural network which will be trained to calculate the squra root of 1000 random numbers generated. but I don't want to use fitnet, instead I want to design my own fitting network. can any one tell me the architecture of fitnet used in matlab means how many layers, initializing functions, training functions etc used.
MATLAB: How to design the own fitting neural network
Deep Learning Toolboxfitnet architecture
Related Question
- Neural network (fitnet) and data decomposition
- Question about neural network weights/biases initialization
- I hv attached the script generated for 2 layer(1 hidden layer) NN , what changes do i need to make to use it for NN with more than 1 hidden layer.
- Can custom neural networks use validation and test sets
- How to train a feedfordward neural network with error weights
Best Answer