Recurrent Neural Network
الشبكة العصبية التكرارية
Definition
A neural network for processing sequences that keeps a hidden state passed from one time step to the next, so it remembers what came earlier in the sequence.
Definition
A recurrent neural network processes sequences by applying the same weights at each time step and carrying a hidden state that summarises the sequence seen so far.
Mathematical equations
h_t = \tanh\left(W_{xh} x_t + W_{hh} h_{t-1} + b_h\right)Scientific sources
References and scientific sources
-
Research paperFinding Structure in Time The simple recurrent neural network (Elman network).
-
Research paperLong Short-Term Memory The LSTM architecture, addressing the vanishing gradient problem in recurrent networks.
-
BookDeep Learning A comprehensive reference book on deep learning, free to read on the web.
