A Comparison of Sequence-Trained Deep Neural Networks and Recurrent Neural Networks Optical Modeling for Handwriting Recognition.
Théodore BlucheHermann NeyChristopher KermorvantPublished in: SLSP (2014)
Keyphrases
- recurrent neural networks
- handwriting recognition
- echo state networks
- neural network
- feed forward
- recurrent networks
- cascade correlation
- artificial neural networks
- reservoir computing
- feedforward neural networks
- multilayer perceptron
- neural model
- hidden layer
- nonlinear dynamic systems
- character recognition
- speech recognition
- back propagation
- historical documents
- pattern recognition
- word recognition
- genetic algorithm
- bayesian networks
- handwritten text
- handwritten words
- chaotic time series
- word spotting
- noise reduction
- multi layer perceptron