MLP

class behavenet.models.decoders.MLP(hparams)[source]

Bases: behavenet.models.base.BaseModule

Feedforward neural network model.

Methods Summary

build_model()

Construct the model.

forward(x)

Process input data.

Methods Documentation

build_model()[source]

Construct the model.

forward(x)[source]

Process input data.

Parameters

x (torch.Tensor) – shape of (time, neurons)

Returns

  • x (torch.Tensor): mean prediction of model

  • y (torch.Tensor): precision matrix prediction of model (when using ‘mlp-mv’)

Return type

tuple