7
$\begingroup$

I am new to deep learning and LSTM (with keras). I am trying to solve a multi-step ahead time series prediction. I have 3 time series: A, B and C and I want to predict the values of C. I am training an LSTM feeding 3 steps back data points to predict the next 3 steps in the future. The input data looks like:

X = [[[A0, B0, C0],[A1, B1, C1],[A2, B2, C2]],[[ ...]]]

with dimensions: (1000, 3, 3). The output is:

y = [[C3, C4, C5],[C4, C5, C6],...]

with dimensions: (1000, 3).

I am using a simple LSTM with 1 hidden layer (50 neurons). I set up an LSTM with keras as:

n_features = 3
neurons = 50
ahead = 3
model = Sequential()
model.add(LSTM(input_dim=n_features, output_dim=neurons))
model.add(Dropout(.2))
model.add(Dense(input_dim=neurons, output_dim=ahead))
model.add(Activation('linear'))
model.compile(loss='mae', optimizer='adam')
model.fit(X, y, epochs=50)

This model works fine. Now, I'd like to predict the values of B as well (using the same input). So I tried to reshape the output in a similar way as I did for the training that has multiple features:

 y = [[[B3, C3],[B4, C4],[B5, C5]],[[ ...]]]

so that it has dimensions: (1000, 3, 2). However, this gives me an error:

Error when checking target: expected activation_5 to have 2 dimensions, 
but got array with shape (1000, 3, 2)

I guess the structure of the network needs to change. I tried to modify model.add(Dense(input_dim=neurons, output_dim=ahead)) with no success. Should I reshape the y differently? Is the structure of the network wrong?

$\endgroup$
  • $\begingroup$ I am also working on similar problem. Can you please consult me on the way how did you prepare your data in such a way? X = [[[A0, B0, C0],[A1, B1, C1],[A2, B2, C2]],[[ ...]]]? I also have question: when you forecast the next 3 points, did you use the previous 3? But when you want to forecast the 5th did you use the forecasted 4th? Thank you in advance? $\endgroup$ – osaozz Dec 22 '17 at 18:15
  • $\begingroup$ Change the last Dense layer's output to 3, it may solve the problem $\endgroup$ – Kaustabh Ganguly Jul 2 '18 at 8:01
  • $\begingroup$ If you always feed in the same length and output the same length then you don’t really need any sort of RNN, and may get better results if you do not use them. $\endgroup$ – kbrose Jul 2 '18 at 13:43
1
$\begingroup$
model = Sequential()
model.add(LSTM(input_dim=n_features, output_dim=neurons))
model.add(Dropout(.2))
model.add(Flatten())
model.add(Dense(ahead))
model.compile(loss='mae', optimizer='adam')
model.fit(X, y, epochs=50)

The differences include:

  • I'm flattening the output from LSTM, cause it's going to give a 3D tensor and a Dense layer for this scenario I believe is going to expect a 2D tensor.
  • Made the change the change suggested in another answer.
  • Removed the activation layer, since default activation of Keras dense layer is linear.
$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.