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
Deep Diffeomorphic Transformer Networks
TL;DR: This work investigates the use of flexible diffeomorphic image transformations within neural networks and demonstrates that significant performance gains can be attained over currently-used models.
Proceedings ArticleDOI
Unsupervised Multi-Domain Image Translation with Domain-Specific Encoders/Decoders
TL;DR: This work proposes a novel and unified framework named Domain-Bank, which consists of a globally shared auto-encoder and domain-specific encoders/decoders, assuming that there is a universal shared-latent space can be projected and shows the comparable (or even better) image translation results over state-of-the-arts on various challenging unsupervised image translation tasks.
Proceedings Article
Detection of Paroxysmal Atrial Fibrillation using Attention-based Bidirectional Recurrent Neural Networks.
TL;DR: The proposed high accuracy, low false alarm algorithm for detecting paroxysmal AF has potential applications in long-term monitoring using wearable sensors and the cross-domain generalizablity of the approach is demonstrated by adapting the learned model parameters from one recording modality to another with improved AF detection performance.
Book ChapterDOI
Natural Scene Text Understanding
TL;DR: Research on document image analysis entered a new era where breakthroughs are required: traditional document analysis systems fail against this new and promising acquisition mode and main differences and reasons of failures will be detailed in this section.
Posted Content
Neural Kernels Without Tangents
Vaishaal Shankar,Alex Fang,Wenshuo Guo,Sara Fridovich-Keil,Ludwig Schmidt,Jonathan Ragan-Kelley,Benjamin Recht +6 more
TL;DR: This paper investigated the connections between neural networks and simple building blocks in kernel space and found that compositional kernels outperform neural tangent kernels and neural networks outperform both kernel methods in the small dataset regime.