Book ChapterDOI
GradientBased Learning Applied to Document Recognition
Simon Haykin,Bart Kosko +1 more
- pp 306-351
TLDR
Various methods applied to handwritten character recognition are reviewed and compared and Convolutional Neural Networks, that are specifically designed to deal with the variability of 2D shapes, are shown to outperform all other techniques.Abstract:
Multilayer Neural Networks trained with the backpropagation 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, that 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 multi-module systems to be trained globally using Gradient-Based methods so as to minimize an overall performance measure. Two systems for on-line handwriting recognition are described. Experiments demonstrate the advantage of global training, and the flexibility of Graph Transformer Networks. A Graph Transformer Network for reading bank check is also described. It uses Convolutional Neural Network character recognizers combined with global training techniques to provides record accuracy on business and personal checks. It is deployed commercially and reads several million checks per day.read more
Citations
More filters
Proceedings ArticleDOI
Adaptively Connected Neural Networks
TL;DR: AdaptNet as discussed by the authors employs a flexible way to switch global and local inference in processing the internal feature representations by adaptively determining the connection status among the feature nodes (e.g., pixels of the feature maps).
Proceedings ArticleDOI
3DCapsule: Extending the Capsule Architecture to Classify 3D Point Clouds
Ali Cheraghian,Lars Petersson +1 more
TL;DR: The 3DCapsule as discussed by the authors is a 3D extension of the Capsule concept that makes it applicable to unordered point sets, where a new layer called ComposeCaps is introduced that, in lieu of a spatially relevant feature mapping, learns a new mapping that can be exploited by the 3DCapule.
Journal ArticleDOI
A survey on indoor RGB-D semantic segmentation: from hand-crafted features to deep convolutional neural networks
Fahimeh Fooladgar,Shohreh Kasaei +1 more
TL;DR: In this survey, a comprehensive analysis has been carried out on RGB-Depth semantic segmentation methods, their challenges and contributions, availableRGB-Depth datasets, metrics of evaluation, state-of-the-art results, and promising directions of the field.
Posted Content
Generalized Capsule Networks with Trainable Routing Procedure
TL;DR: Generalized CapsNet (G-CapsNet) is implemented, which achieves a similar performance in the dataset MNIST as in the original papers and embeds the routing procedure into the optimization procedure with all other parameters in neural networks.
Proceedings ArticleDOI
X-Ray Scattering Image Classification Using Deep Learning
TL;DR: Convolutional Neural Networks and Convolutional Autoencoders are applied for x-ray scattering image classification and it is shown that deep learning methods outperform previously published methods by 10% on synthetic and real datasets.