combining two neural networks (net1 is trained & net2 is untrained) in one bigger network

I have two shallow neural network models net1, net2.

I have a trained net1. Then I need to connect a net2 to a net1. Hence I treat the combined (net2+net1) as one large net and then train the big net . However, during the second training phase, we only need to update the weights corresponding to net2 (and keep net1 weights fixed). Is it possible in MATLAB? any suggested links or articles to perform this part.

[Xin Yee Tai]

Could you please share the code to build the neural network on the last photo? Thank you.

[Russdsp]

Yes please share code. the green box in the middle doesnt seem like a layer- how is that there?

Answer 1

[Hiro Yoshino]

How about this?:

https://www.mathworks.com/matlabcentral/answers/497749-avoid-training-certain-neurons#answer_407422?s_tid=prof_contriblnk

[Abdelwahab Afifi]

what about connecting two neural networks with each other?

[Abdelwahab Afifi]

After training, how can I extract net2 from the big net ?

Answer 2

[Greg Heath]

Just

1. Save the outputs of net1 in a file

2. Use the file to train net2

Greg

[Beatriz Martins]

Greg Heath,

I am trying to save the output of a net1 and use it to train net2. However, during training of net1 the trainFasterRCNNObjectDetector function added new layers (initially I have 25 layers and the output of net1 has 35) and I get an invalid network. Do you know how can I solve this problem?

[Abdelwahab Afifi]

Greg Heath,

more clarification please. I wanna train the bigger networok which combined of (untrained net2 + trained net1)