Deleting some layers from trained neural network model

I have trained a big neural network NN which has the structure [20 2 20] as shown in the first figure. After training, I wanna separate/copy/keep the first part of the network [20 2] and save its wights, biases, and connections as shown in the second figure. How can I do so?

Answer 1

[Bhargavi Maganuru]

Hi,

You can get weights, biases of feedforward network using network object parameters IW,LW,b

You can refer following links for more information

https://www.mathworks.com/help/deeplearning/ug/neural-network-object-properties.html#bss4hk6-60

https://www.mathworks.com/help/deeplearning/ug/neural-network-subobject-properties.html#bss4hk6-136