Closed CSFelix closed 1 year ago
Now, even though RNNs are quite powerful, they suffer from Vanishing Gradient Problem which hinders them from using long term information, like they are good for storing memory 3-4 instances of past iterations but larger number of instances don't provide good results so we don't just use regular RNNs. Instead, we use a better variation of RNNs: Long Short Term Networks (LSTM).
Components of LSTMs
Forget Gate “f” ( a neural network with sigmoid);
Candidate layer “C"(a NN with Tanh);
Input Gate “I” ( a NN with sigmoid );
Output Gate “O”( a NN with sigmoid);
Hidden state “H” ( a vector );
Memory state “C” ( a vector);
Inputs to the LSTM cell at any step are Xt (current input) , Ht-1 (previous hidden state ) and Ct-1 (previous memory state);
Outputs from the LSTM cell are Ht (current hidden state ) and Ct (current memory state);
There's no need to use LSTM and GRU since the dataset is not a Time Series at all.
Models
Intro to Keras with breast cancer data[ANN]
Intro to Recurrent Neural Networks LSTM | GRU