How to Use RegressionLayer in LSTM of Nerual Network Toolbox?

• I want to build a network:
• input layer:64 units ----> hidden layer (LSTM): 1024 units ----> output layer(Fully connect + softmax):64 units
• output's type is a float number in [0,1]
• The question is how can i use lstm in Nerual Network Toolbox to build a network

Answer 1

[Wentao Du]

Please refer to the following example in documentation:

https://www.mathworks.com/help/nnet/examples/classify-sequence-data-using-lstm-networks.html

Answer 2

[Wentao Du]

In the newest release of MATLAB R2018a, LSTM can be used for regression problems: https://www.mathworks.com/help/releases/R2018a/nnet/release-notes.html

For an example showing how to forecast future values in a time series, see Time Series Forecasting Using Deep Learning .

For an example showing how to create an LSTM network for sequence-to-sequence regression, see Sequence-to-Sequence Regression Using Deep Learning .