LSTM Class

LSTM Deep Learning Model

Based on model proposed by Yee-King et al. 1

class spiegelib.estimator.LSTM(input_shape, num_outputs, **kwargs)

Bases: spiegelib.estimator.tf_estimator_base.TFEstimatorBase

Parameters

• input_shape (tuple) – Shape of matrix that will be passed to model input

• num_outputs – Number of outputs the model has

• kwargs – optional keyword arguments to pass to spiegelib.estimator.TFEstimatorBase

build_model(highway_layers=100)

Construct LSTM Model

Parameters

highway_layers (int, optional) – dimensionality of outer space of hidden layers, defaults to 100

1

Yee-King, Matthew John, Leon Fedden, and Mark d’Inverno. “Automatic programming of VST sound synthesizers using deep networks and other techniques.” IEEE Transactions on Emerging Topics in Computational Intelligence 2.2 (2018): 150-159.