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. (e.g., In seq2seq, abc => [[[1,0,0],[0,1,0],[0,0,1]]])

However, since I have to predict the x and 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?


Your Answer

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

Browse other questions tagged or ask your own question.