Frank is a bot that does science. He takes a dataset and forms hypothesises about mathematical constants (aka conservation laws) of the data. He then tests the hypothesis.
We use ANNs to represent random functions. Should we? What could one use instead?
Taylor series, Fourier series or a linear combination of a bunch of compactly supported basis functions, maybe?
I don't know. We should probably try some stuff and see what works best.
We use ANNs to represent random functions. Should we? What could one use instead? Taylor series, Fourier series or a linear combination of a bunch of compactly supported basis functions, maybe?
I don't know. We should probably try some stuff and see what works best.