When initializing a neural network with the NEWFF function, I noticed that the sample input and output matrices are stored in the model itself (net.inputs{1}.exampleInput). When having huge training data sets, this would consume too much memory. The data and models should be decoupled and not stored together.
MATLAB: Are the sample input and output matrices stored in the model itself (net.inputs{1}.exampleInput) in Neural Network Toolbox 6.0 (R2008a)
Deep Learning Toolbox
Related Question
- Neural network training function
- Do I get a dimension mismatch error when training the neural network using constant input data in Neural Network Toolbox 6.0 (R2008a)
- How to avoid negative values in the output of a feedforward net
- How to test and improve multi layer perceptron
- How to read result of sim using Patternnet
- Neural Network Toolbox Example Dataset Error – Index Exceeds Matrix Dimensions
- Adding new test dataset to Neural Network
Best Answer