A neural network that is used for analyzing data that is presented as a series. For example, every word in speech and natural language recognition is highly dependent on the words before and after it. The recurrent neural network (RNN) takes the previous analysis into consideration, and the output of various nodes affects the input to the very same nodes. Contrast with
convolutional neural network, which is a widely used AI architecture for recognizing grid patterns such as images. See
neural network and
AI transformer.