Gradient-based learning applied to document recognition

@inproceedings{LeCun1998GradientbasedLA,
  title={Gradient-based learning applied to document recognition},
  author={Yann LeCun and L{\'e}on Bottou and Yoshua Bengio and Patrick Haffner},
  year={1998}
}
Multilayer neural networks trained with the back-propagation algorithm constitute the best example of a successful gradient based learning technique. [...] Key Method 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…Expand
Neural Network Based Handwritten Digits Recognition- An Experiment and Analysis
TLDR
Different network structures and their corresponding recognition rates are compared in this paper to find the optimal parameters of the Neural Network for this application. Expand
Neural Networks for Handwriting Recognition
TLDR
In this chapter a novel kind of Recurrent Neural Networks (RNNs) is described, specifically designed for sequence labeling tasks where the data is hard to segment and contains long-range, bidirectional or multidirectional interdependencies. Expand
Ada-boosting Extreme learning machines for handwritten digit and digit strings recognition
  • Raid Saabni
  • Computer Science
  • 2015 Fifth International Conference on Digital Information Processing and Communications (ICDIPC)
  • 2015
TLDR
Very high accurate results in terms of very low error rates while keeping efficient time of online training were achieved by the presented approach, which enables on demand time/precision tradeoff. Expand
Object Recognition with Gradient-based Learning 1 Learning the Right Features
Finding an appropriate set of features is an essential problem in the design of shape recognition systems. This paper attempts to show that for recognizing simple objects with high shape variabilityExpand
Handwritten Digits Recognition Using SVM, KNN, RF and Deep Learning Neural Networks
TLDR
Several classification algorithms of recognizing numbers from photographic images or with manual input, namely: support vector machine (SVM), Knearest neighbors (KNN), random forest (RF) and several variants of neural networks are discussed. Expand
AN ENSEMBLE OF CONVOLUTIONAL NEURAL NETWORKS FOR THE RECOGNITION OF HANDWRITTEN DIGITS
This paper describes a neural network ensemble that is made up of 8 convolutional networks that are based on the Lenet-5 architecture, with a denser network, the addition of a personal bias for eachExpand
Artificial neural networks for document analysis and recognition
  • S. Marinai, M. Gori, G. Soda
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2005
TLDR
This paper surveys the most significant problems in the area of offline document image processing, where connectionist-based approaches have been applied and depicts the most promising research guidelines in the field. Expand
Multi-modular architecture based on convolutional neural networks for online handwritten character recognition
TLDR
In this paper, several convolutional neural network architectures are investigated for online isolated handwritten character recognition (Latin alphabet) and an hybrid architecture called SDTDNN has been derived, it allows the combination of on-line and off-line recognisers. Expand
Neural network based off-line handwritten text recognition system
TLDR
This dissertation introduces a new system for handwritten text recognition based on an improved neural network design that utilizes the mean quartic error function, where the third and fourth derivatives are non-zero. Expand
A Lightweight Handwriting Recognition System Based on an Improved Convolutional Neural Network
TLDR
A new improved handwritten character recognition method of convolutional neural network is proposed, which adds Batch Normalization Layer and Residual Network Structure to the general convolutionAL neural network, and adopts multi-scale prediction method. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 249 REFERENCES
Off Line Recognition of Handwritten Postal Words Using Neural Networks
TLDR
A method, “Shortest Path Segmentation” (SPS), which combines dynamic programming and a neural net recognizer for segmenting and recognizing character strings is described, and applications of some of these ideas are described. Expand
Handwritten Digit Recognition Using K Nearest-Neighbor, Radial-Basis Function, and Backpropagation Neural Networks
  • Yuchun Lee
  • Medicine, Computer Science
  • Neural Computation
  • 1991
TLDR
These results on a large, high input dimensional problem demonstrate that practical constraints including training time, memory usage, and classification time often constrain classifier selection more strongly than small differences in overall error rate. Expand
Comparing different neural network architectures for classifying handwritten digits
TLDR
The authors propose a novel way of organizing the network architectures by training several small networks so as to deal separately with subsets of the problem, and then combining the results. Expand
Connectionist architectural learning for high performance character and speech recognition
  • U. Bodenhausen, S. Manke
  • Computer Science
  • 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1993
TLDR
The authors applied an automatic structure optimization (ASO) algorithm to the optimization of multistate time-delay neural networks (MSTDNNs), an extension of the TDNN, which was applied successfully to speech recognition and handwritten character recognition tasks with varying amounts of training data. Expand
A system for the off-line recognition of handwritten text
  • T. Breuel
  • Computer Science
  • Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5)
  • 1994
TLDR
A new system for the recognition of handwritten text that goes from raw, binary scanned images of census forms to ASCII transcriptions of the fields contained within the forms, using two different statistical language models. Expand
Distortion Invariant Object Recognition in the Dynamic Link Architecture
TLDR
An object recognition system based on the dynamic link architecture, an extension to classical artificial neural networks (ANNs), is presented and the implementation on a transputer network achieved recognition of human faces and office objects from gray-level camera images. Expand
A connectionist recognizer for on-line cursive handwriting recognition
  • S. Manke, U. Bodenhausen
  • Computer Science
  • Proceedings of ICASSP '94. IEEE International Conference on Acoustics, Speech and Signal Processing
  • 1994
TLDR
The MS-TDNN integrates the high accuracy single character recognition capabilities of a TDNN with a non-linear time alignment procedure (dynamic time warping algorithm) for finding stroke and character boundaries in isolated, handwritten characters and words. Expand
Face recognition: a convolutional neural-network approach
TLDR
A hybrid neural-network for human face recognition which compares favourably with other methods and analyzes the computational complexity and discusses how new classes could be added to the trained recognizer. Expand
Neural networks for speech and sequence recognition
TLDR
This paper presents post-processors based on dynamic programming ANN/DP hybrids ANN/HMM Hybrids, and experiments on phoneme recognition with RBFs and online handwriting recognition experiments. Expand
Multi-Digit Recognition Using a Space Displacement Neural Network
TLDR
A feed-forward network architecture for recognizing an unconstrained handwritten multi-digit string with segmentation done on the feature maps developed in the Space Displacement Neural Network rather than the input (pixel) space. Expand
...
1
2
3
4
5
...