0xDeCA10B
0xDeCA10B copied to clipboard
[simulation] Use normalization like in the demo.
In the demo, normalization is done before updating the dense perceptron and dense nearest centroid classifiers, but the simulation doesn't use normalization.
Normalization is used to avoid submissions with large values that would corrupt the model. Using normalized vectors might be bad for these models but it seems like a necessary guard to have on-chain.
Can you describe more about this Issue?
We enforce that data in normalized before adding in DensePerceptron.sol and some other classes in the demo folder but we don't normalize data before processing it in the simulation.