Residual Recurrent Neural Network with Sparse Training for Offline Arabic Handwriting Recognition.
Ruijie YanLiangrui PengGuangXiang BinShengjin WangYao ChengPublished in: ICDAR (2017)
Keyphrases
- recurrent neural networks
- recurrent networks
- feedforward neural networks
- echo state networks
- neural network
- neural network structure
- arabic handwriting recognition
- complex valued
- feed forward neural networks
- feed forward
- hidden layer
- reservoir computing
- real time
- neural model
- training process
- sparse data
- training algorithm
- training set
- artificial neural networks
- hebbian learning
- image processing
- avoid overfitting
- multi layer perceptron
- supervised learning
- biologically inspired
- convergence rate
- feature extraction
- machine learning
- training samples
- recognition rate