Recurrent neural network

A recurrent neural network (RNN) is a class of artificial neural networks where connections between nodes form a directed graph along a temporal sequence. This allows it to exhibit temporal dynamic behavior.

Derived from feedforward neural networks, RNNs can use their internal state (memory) to process variable length sequences of inputs. This makes them applicable to tasks such as unsegmented, connected handwriting recognitionor speech recognition.

Extra reading:

Introduction to Recurrent Neural Network

Papers:

  1. Hierarchical RNN – Paper
  2. LSTM – http://deeplearning.cs.cmu.edu/p…
  3. Neural Turing Machines – http://arxiv.org/pdf/1410.5401
  4. Memory Networks – Paper
  5. Speech Recognition with Deep RNN – Paper
  6. Attention based mechanism in RNN – Paper
  7. Scene labelling using RNN – Paper
  8. CRFs as RNN – Paper

Video:

Leave a Reply

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Convolutional Recurrent Neural Networks (CRNN)

Object detection