Retrieve dataloaders and visualization function. Example: load_data, visualize_data = initialize_data_functions(args) d

This method should set self.dataset_train, self.dataset_val, and self.dataset_test

> `time_features` takes in a `dates` dataframe with a 'dates' column and extracts the date down to `freq` where freq can be any of the following

Returns a list of time features that will be appropriate for the given frequency string. Parameters ---------- freq_str Frequ

Fully-connected network

tie: tie dropout mask across sequence lengths (Dropout1d/2d/3d)

Generic class for encoding

Assumes z is pure imaginary (as in S4 with bilinear)

v: (..., N) z: (..., L) w: (..., N) returns: (..., L) \sum v/(z-w)

Invert the causal convolution/polynomial/triangular Toeplitz matrix represented by u. This is easiest in the polynomial view: https://www.cs

batch: list of (x, y) pairs