my question is: this NEAT algorithm works well on XOR-experiment(2 input and 2 output), but I use it on a 3-input function, it works less efficient than XOR-experiment.

[ZhideLu]

Describe the bug
A clear and concise description of what the bug is.

To Reproduce
Steps to reproduce the behavior:

1. Go to '...'
2. Click on '....'
3. Scroll down to '....'
4. See error

Expected behavior
A clear and concise description of what you expected to happen.

Screenshots
If applicable, add screenshots to help explain your problem.

• OS: [e.g. iOS]
• Version [e.g. 22]

Additional context
Add any other context about the problem here.

[ZhideLu]

so how can this algorithm be scaled up to function with more input node, not only the XOR-function ?

[ddehueck]

Sorry, this slipped by me. To answer your question, this method inherently does not scale well. Any growth to the input to the network affects the entire population which means we have a growth on the order of population_size * network_size.

However, if this issue refers to something like it takes an unreasonable amount of time on a toy problem like the XOR problem but with only 3 inputs then please provide the details and I may be able to help from there.