Recurrent Neural Network (RNN) is a type of artificial neural network designed for processing sequential data.
The main differences between a RNN and a traditional feedforward neural network revolve around how they process data, especially with respect to sequential and temporal data.
In RNN, the hidden state at each time step depends on the hidden states from previous time steps.
The parameters (weights and biases) are updated using an optimization algorithm like Stochastic Gradient Descent (SGD).