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
Posted Content
Evolving Space-Time Neural Architectures for Videos
TL;DR: In this article, an evolutionary search algorithm is proposed to automatically explore models with different types and combinations of layers to jointly learn interactions between spatial and temporal aspects of video representations, which can capture rich spatio-temporal information in videos.
Journal ArticleDOI
Binary Morphological Filtering of Dominant Scattering Area Residues for SAR Target Recognition.
Chao Shan,Bin Huang,Minggao Li +2 more
TL;DR: A synthetic aperture radar (SAR) target recognition method based on the dominant scattering area (DSA), which can reflect the distribution of the scattering centers as well as the preliminary shape of the target, thus providing discriminative information for SAR target recognition.
Proceedings Article
Scalable Differential Privacy with Certified Robustness in Adversarial Learning
TL;DR: A scalable algorithm to preserve differential privacy (DP) in adversarial learning for deep neural networks (DNNs), with certified robustness to adversarial examples, is developed by leveraging the sequential composition theory in DP.
Proceedings ArticleDOI
Cellular Network Radio Propagation Modeling with Deep Convolutional Neural Networks
TL;DR: A novel method to model radio propagation using deep convolutional neural networks is presented and significantly improved performance is reported compared to conventional models.
Posted Content
SpArSe: Sparse Architecture Search for CNNs on Resource-Constrained Microcontrollers
TL;DR: It is demonstrated that it is possible to automatically design CNNs which generalize well, while also being small enough to fit onto memory-limited MCUs, and the CNNs found are more accurate and up to $4.35 times smaller than previous approaches, while meeting the strict MCU working memory constraint.