Recurrent neural network

lastmod 2026-10-30created 2015-10-2619 edits

A recurrent neural network (RNN) is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. This makes them applicable to tasks such as unsegmented connected handwriting recognition or speech recognition

Category

• Backpropagation through time (BPTT)
• LSTM
• Recurrent Neural Network Regularization
• Arithmetic mean: see computing the mean of continuous input values.
• Gated recurrent unit (GRU)

AI Korea - Recurrent Neural Network (RNN) Tutorial

• Recurrent Neural Network (RNN) Tutorial - Part 1
  • Original: Recurrent Neural Networks Tutorial, Part 1 – Introduction to RNNs
• RNN Tutorial Part 2 - Implementing an RNN with Python, NumPy and Theano
• RNN Tutorial Part 3 - BPTT and the Vanishing Gradient problem
• RNN Tutorial Part 4 - Implementing a GRU/LSTM RNN with Python and Theano

See also

• Deep learning
• Vanishing gradient problem
• LSTM
• GCN
• T-GCN

Favorite site

• Wikipedia (en) Description of RNN
• Recurrent neural network - Namuwiki
• 08-01 Recurrent Neural Network (RNN) - Introduction to natural language processing with deep learning - from RAG and agents to LLM fine-tuning
• What is an RNN? - Recurrent neural networks explained - AWS
• [Recommended] Understanding LSTM Networks
  • Kor ver: Recurrent Neural Network (RNN) and LSTM ¹
• A beginner's guide to RNNs and LSTMs ²
• [Recommended] Machine Learning Revolution - RNN and LSTM - Don't be intimidated by deep learning ³ (Modulabs - DeepLAB)
• Recursive Neural Networks - ratsgo's blog
• Effective RNN training - ratsgo's blog
• Let's understand RNN and LSTM! - ratsgo's blog

References