Open Mariam-124 opened 6 months ago
Hi , I am trying to use a multivariant LST model for stock price prediction , and that model defines output dimension which is different from input dimension. But I am unable to understand how to add output dimension in NCP.
Previous model: _model = Sequential() model.add(LSTM(64, activation='relu', input_shape=(trainX.shape[1], trainX.shape[2]), return_sequences=True)) model.add(LSTM(32, activation='relu', returnsequences=False)) model.add(Dropout(0.2)) model.add(Dense(trainY.shape[1]))
My LTC Model is
wiring = wirings.AutoNCP(8,1) # 8 neurons in total, 1 output (motor neuron) model = keras.models.Sequential( [ keras.layers.InputLayer(input_shape=(None, 5)),
LTC(wiring, return_sequences=True), ]
) model.compile( optimizer=keras.optimizers.Adam(0.01), loss='mean_squared_error' )
model.summary()
as I want my output to be 2 dimensional but this gives same output dimensions as input dimensions a 3
so please guide me as examples in docs only shows same input output dimensions
Hi , I am trying to use a multivariant LST model for stock price prediction , and that model defines output dimension which is different from input dimension. But I am unable to understand how to add output dimension in NCP.
Previous model: _model = Sequential() model.add(LSTM(64, activation='relu', input_shape=(trainX.shape[1], trainX.shape[2]), return_sequences=True)) model.add(LSTM(32, activation='relu', returnsequences=False)) model.add(Dropout(0.2)) model.add(Dense(trainY.shape[1]))
My LTC Model is
wiring = wirings.AutoNCP(8,1) # 8 neurons in total, 1 output (motor neuron) model = keras.models.Sequential( [ keras.layers.InputLayer(input_shape=(None, 5)),
here we could potentially add layers before and after the LTC network
) model.compile( optimizer=keras.optimizers.Adam(0.01), loss='mean_squared_error' )
model.summary()
as I want my output to be 2 dimensional but this gives same output dimensions as input dimensions a 3
so please guide me as examples in docs only shows same input output dimensions