Recurrent neural network

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
• 산술 평균 (Arithmetic mean): 지속적인 입력값에 대한 평균 산출을 참조.
• 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 - Python, NumPy와 Theano로 RNN 구현하기
• RNN Tutorial Part 3 - BPTT와 Vanishing Gradient 문제
• RNN Tutorial Part 4 - GRU/LSTM RNN 구조를 Python과 Theano를 이용하여 구현하기

See also

• Deep learning
• Vanishing gradient problem

Favorite site

• Wikipedia (en) RNN에 대한 설명
• [추천] Understanding LSTM Networks
  • Kor ver: Recurrent Neural Network (RNN) 과 LSTM ¹
• 초보자를 위한 RNNs과 LSTM 가이드 ²
• [추천] 머신러닝레볼루션 - RNN과 LSTM - 쫄지말자 딥러닝 ³ (모두의연구소 - DeepLAB)
• Recursive Neural Networks - ratsgo's blog
• 효과적인 RNN 학습 - ratsgo's blog
• RNN과 LSTM을 이해해보자! - ratsgo's blog

References