FluxArchitectures.jl
FluxArchitectures.jl copied to clipboard
DA-RNN Multi-step Prediction
As DA-RNN is basically a encoder-decoder network, how would you do multi step prediction in the decoder phase?
Good question - doing multi-step prediction is not in my use case for these models, so unfortunately I am not an expert on that. You might have a look at implementations for other programming languages and see how it is done there.
I'll be looking into it