Knowledge Graph — Coursera Notes › Academic disciplines › Computer Science / Information Technology › Artificial Intelligence › Deep Learning

RNN

concept · part of Deep Learning

A neural network architecture for sequential data where input order matters, processing tokens one by one. RNNs maintain a hidden state memory of previous inputs, and advanced variants like LSTM and GRU address long-term dependencies, making them suitable for time-series forecasting and NLP.

They excel at tasks like time series forecasting, language translation, and sentiment analysis, e.g., predicting stock prices based on historical data.

Connections

• Alternative to Transformer
• Related to LSTM

This is the text view of an interactive 3D knowledge graph — open this page with JavaScript enabled to explore it visually.