RNN

Recurrent Neural Network

A type of artificial neural network architecture designed to handle sequential or time-series data. Unlike feedforward neural networks, RNNs have connections between neurons that form directed cycles, allowing them to maintain an internal state or memory of previous inputs in the sequence. This feature makes RNNs particularly well-suited for tasks involving sequences, such as natural language processing, speech recognition, and time-series prediction.

In an RNN, the output at a given time step is influenced by both the current input and the hidden state from the previous time step. This enables the network to learn patterns and dependencies across different positions within the input sequence.

However, RNNs have some limitations, including difficulty in learning long-range dependencies due to the vanishing gradient problem. This issue has been partially addressed by more advanced RNN architectures, such as Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRUs), which introduce specialized gating mechanisms to help the network learn and retain long-term dependencies more effectively.

• Abbreviation: RNN