Multidimensional time series | MATLAB implements BiLSTM bidirectional long-term short-term memory neural network multivariate time series prediction (multi-index evaluation)

Multidimensional time series | MATLAB implements BiLSTM bidirectional long-term short-term memory neural network multivariate time series prediction (multi-index evaluation)

List of effects

1
2
3

basic introduction

The so-called Bi-LSTM and Bi-RNN can be regarded as a two-layer neural network. The first layer is used as the initial input of the sequence from the left, which can be understood as input from the beginning of the sequence in terms of timing, while the second layer is From the right as the starting input of the series, in terms of timing processing, it can be understood as starting from the last input of the sequence, and doing the same processing as the first layer in reverse. Finally, process the two obtained results.

Guess you like

Origin blog.csdn.net/kjm13182345320/article/details/130048607