阅读量：

81424

作者：

Y Lecun，L Bottou

展开

摘要：

Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. Given an appropriate network architecture, gradient-based learning algorithms can be used to synthesize a complex decision surface that can classify high-dimensional patterns, such as handwritten characters, with minimal preprocessing. This paper reviews various methods applied to handwritten character recognition and compares them on a standard handwritten digit recognition task. Convolutional neural networks, which are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques. Real-life document recognition systems are composed of multiple modules including field extraction, segmentation recognition, and language modeling. A new learning paradigm, called graph transformer networks (GTN), allows such multimodule systems to be trained globally using gradient-based methods so as to minimize an overall performance measure. Two systems for online handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of graph transformer networks. A graph transformer network for reading a bank cheque is also described. It uses convolutional neural network character recognizers combined with global training techniques to provide record accuracy on business and personal cheques. It is deployed commercially and reads several million cheques per day.

展开

关键词：

backpropagation convolution multilayer perceptrons optical character recognition 2D shape variability GTN back-propagation cheque reading complex decision surface synthesis convolutional neural network character recognizers document recognition document recognition systems field extraction gradient based learning technique gradient-based learning graph transformer networks handwritten character recognition handwritten digit recognition task high-dimensional patterns language modeling multilayer neural networks multimodule systems performance measure minimization segmentation recognition

DOI：

10.1109/5.726791

被引量：

1.6万

年份：

1998