I want to design a simple model that predicts the movement of coordinates with RNNs.
In a typical three-dimensional LSTM model, one feature is encoded as one hot encoding, and the
x value is input as a three-dimensional matrix.
abc => [[[1,0,0],[0,1,0],[0,0,1]]])
However, since I have to predict the
y coordinate values, one hot encoding will inevitably produce a four-dimensional matrix.
What should I do with back-propagation? Or should I design a 3-D matrix using scalar values without one hot encoding?