Click here to Skip to main content
15,064,166 members
Please Sign up or sign in to vote.
0.00/5 (No votes)
See more: , +
Hello -

I am new to the ML scene and I am trying to understand the best practice for designing neural networks that "feed" other neural networks.

For instance in the following example (image) we have two networks (1 & 2) which are using input data feed by a file. They were trained on 80% of this file. Network 3 gets its inputs from the OUTPUTS of the previous two neural networks.

My questions are the following:

1. Would I simply code three separate neural networks, run the first two and take their outputs and feed it to the third?
2. How would you go about training the third neural network? Would I create a separate file and manually recognize the patterns that should be found in 1&2 and their expected output?


This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)

CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900