how does LSTM and GRU gates decide which word to keep in the memory

288 views Asked by At

the update gate in a GRU decides which word to keep in the cell or to be clear what is the cell state. how does the update gate in gru decide when to be close to 1 and when to be close to 0? Basically, how does it decide to keep a word and not to keep a word? Thanks

1

There are 1 answers

0
emschorsch On BEST ANSWER

It's unclear what background research you've done in the question. Perhaps a google search for gru tutorials might turn up some helpful blogs. Here is one.

Remember though the cell state is updated using weights which are optimized the same way any other neural network weights are, with backpropagation. This is a great blog to help explain how RNNs (GRU is one specific example) are set up and how backpropagation through time is used to update the weights. The weights of the GRU then determine how the cell state is updated.