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.

Gradient-based learning applied to document recognition

Machine Learning is the study of methods for programming computers to learn. Computers are applied to a wide range of tasks, and for most of these it is relatively easy for programmers to design and implement the necessary software. However, there are many tasks for which this is difficult or impossible. These can be divided into four general categories. First, there are problems for which there exist no human experts. For example, in modern automated manufacturing facilities, there is a need to predict machine failures before they occur by analyzing sensor readings. Because the machines are new, there are no human experts who can be interviewed by a programmer to provide the knowledge necessary to build a computer system. A machine learning system can study recorded data and subsequent machine failures and learn prediction rules. Second, there are problems where human experts exist, but where they are unable to explain their expertise. This is the case in many perceptual tasks, such as speech recognition, hand-writing recognition, and natural language understanding. Virtually all humans exhibit expert-level abilities on these tasks, but none of them can describe the detailed steps that they follow as they perform them. Fortunately, humans can provide machines with examples of the inputs and correct outputs for these tasks, so machine learning algorithms can learn to map the inputs to the outputs. Third, there are problems where phenomena are changing rapidly. In finance, for example, people would like to predict the future behavior of the stock market, of consumer purchases, or of exchange rates. These behaviors change frequently, so that even if a programmer could construct a good predictive computer program, it would need to be rewritten frequently. A learning program can relieve the programmer of this burden by constantly modifying and tuning a set of learned prediction rules. Fourth, there are applications that need to be customized for each computer user separately. Consider, for example, a program to filter unwanted electronic mail messages. Different users will need different filters. It is unreasonable to expect each user to program his or her own rules, and it is infeasible to provide every user with a software engineer to keep the rules up-to-date. A machine learning system can learn which mail messages the user rejects and maintain the filtering rules automatically. Machine learning addresses many of the same research questions as the fields of statistics, data mining, and psychology, but with differences of emphasis. Statistics focuses on understanding the phenomena that have generated the data, often with the goal of testing different hypotheses about those phenomena. Data mining seeks to find patterns in the data that are understandable by people. Psychological studies of human learning aspire to understand the mechanisms underlying the various learning behaviors exhibited by people (concept learning, skill acquisition, strategy change, etc.).

Machine learning

The primary goal of pattern recognition is supervised or unsupervised classification. Among the various frameworks in which pattern recognition has been traditionally formulated, the statistical approach has been most intensively studied and used in practice. More recently, neural network techniques and methods imported from statistical learning theory have been receiving increasing attention. The design of a recognition system requires careful attention to the following issues: definition of pattern classes, sensing environment, pattern representation, feature extraction and selection, cluster analysis, classifier design and learning, selection of training and test samples, and performance evaluation. In spite of almost 50 years of research and development in this field, the general problem of recognizing complex patterns with arbitrary orientation, location, and scale remains unsolved. New and emerging applications, such as data mining, web searching, retrieval of multimedia data, face recognition, and cursive handwriting recognition, require robust and efficient pattern recognition techniques. The objective of this review paper is to summarize and compare some of the well-known methods used in various stages of a pattern recognition system and identify research topics and applications which are at the forefront of this exciting and challenging field.

/pdf/statistical-pattern-recognition-a-review-1kz1b0tte4.pdf

Statistical pattern recognition: a review

We develop a common theoretical framework for combining classifiers which use distinct pattern representations and show that many existing schemes can be considered as special cases of compound classification where all the pattern representations are used jointly to make a decision. An experimental comparison of various classifier combination schemes demonstrates that the combination rule developed under the most restrictive assumptions-the sum rule-outperforms other classifier combinations schemes. A sensitivity analysis of the various schemes to estimation errors is carried out to show that this finding can be justified theoretically.

On combining classifiers

From the Publisher:
Pattern recognition has long been studied in relation to many different (and mainly unrelated) applications, such as remote sensing, computer vision, space research, and medical imaging. In this book Professor Ripley brings together two crucial ideas in pattern recognition; statistical methods and machine learning via neural networks. Unifying principles are brought to the fore, and the author gives an overview of the state of the subject. Many examples are included to illustrate real problems in pattern recognition and how to overcome them.This is a self-contained account, ideal both as an introduction for non-specialists readers, and also as a handbook for the more expert reader.

Pattern recognition and neural networks

Feature selection for ensembles has shown to be an effectivestrategy for ensemble creation. In this paper we presentan ensemble feature selection approach based on a hierarchicalmulti-objective genetic algorithm. The first level performsfeature selection in order to generate a set of goodclassifiers while the second one combines them to providea set of powerful ensembles. The proposed method is evaluatedin the context of handwritten digit recognition, usingthree different feature sets and neural networks (MLP) asclassifiers. Experiments conducted on NIST SD19 demonstratedthe effectiveness of the proposed strategy.

/pdf/feature-selection-for-ensembles-a-hierarchical-multi-34wzce8knd.pdf

Feature selection for ensembles:a hierarchical multi-objective genetic algorithm approach

A method of recognizing unconstrained handwritten numerals using a knowledge base is proposed. Features are collected from a training set and stored in a knowledge base that is used in the recognition stage. Recognition is accomplished by either an inference process or a structural method. The scheme is general, flexible, and applicable to different methods of feature extraction and recognition. By changing the acceptance parameters, a continuous range of performance can be achieved. Encouraging results on nearly 17000 totally unconstrained handwritten numerals are presented. The performance of the system under different recognition-rejection tradeoff ratios is analyzed in detail. >

A generalized knowledge-based system for the recognition of unconstrained handwritten numerals

I. Review of Basic Algorithms.- An Overview of Digital Techniques for Progessing Speech Signals.- Systems for Isolated and Connected Word Recognition.- II. System Architecture and Vlsi for Speech Processing.- Systolic Architectures for Connected Speech Recognition.- Computer Systems for High-Performance Speech Recognition.- VLSI Architectures for Recognition of Context-Free Languages.- Implementation of an Aeoustical Front-End for Speech Recognition.- Reconfigurable Modular Architecture for a Man-Machine Vocal Communication System in Real Time.- A Surrey of Algorithms & Architecture for Connected Speech Recognition.- III. Software Systems for Automatic Speech Recognition.- Knowledge-Based and Expert Systems in Automatic Speech Recognition.- The Speech Understanding and Dialog System EVAR.- A New Rule-Based Expert System for Speech Recognition.- SAY - A PC Based Speech Analysis System.- Automatic Generation of Linguistic, Phonetic and Acoustic Knowledge for a Diphone-Based Continuous Speech Recognition System.- The Use of Dynamic Frequency Warping in a Speaker-Independent Vowel Classifier.- Dynamic Time Warping Algorithms for Isolated and Connected Word Recognition.- An Efficient Algorithm for Recognizing Isolated Turkish Words.- A General Fuzzy-Parsing Scheme for Speech Recognition.- IV Speech Synthesis and Phonetics.- Linguistics and Automatic Processing of Speech.- Synthesis of Speech by Computers and Chips.- Prosodic Knowledge in the Rule-Based Synthex Expert System for Speech Synthesis.- Syntex - Unrestricted Conversion of Text to Speech for German.- Concatenation Rules for Demisyllable Speech Synthesis.- On the Use of Phonetic Knowledge for Automatic Speech Recognition.- Demisyllables as Processing Units for Automatic Speech Recognition and Lexical Access.- Detection and Recognition of Nasal Consonants in Continuous Speech - Preliminary Results.- Author Index.

New Systems and Architectures for Automatic Speech Recognition and Synthesis

A new direction in machine learning area has emerged from Vapnik's theory in support vectors machine (SVM) and its applications on pattern recognition. In this paper we propose a new SVM kernel family, called KMOD (kernel with moderate decreasing) with distinctive properties that allow better discrimination in the feature space. The experiments that we carry out show its effectiveness on synthetic and large-scale data. We found KMOD performs better than RBF and exponential RBF kernels on the two-spiral problem. In addition, a digit recognition task was processed using the proposed kernel. The results show, at least, comparable performances to state of the art kernels.

/pdf/kmod-a-new-support-vector-machine-kernel-with-moderate-4o72a4twnd.pdf

KMOD - a new support vector machine kernel with moderate decreasing for pattern recognition. Application to digit image recognition

This paper summarizes the research activities of the pastdecade on the recognition of handwritten scripts used inChina, Japan, and Korea. It presents the recognitionmethodologies, features explored, databases used, andclassification schemes investigated. In addition, it includes adescription of the performance of numerous recognitionsystems found in both academic and industrial researchlaboratories. Recent achievements and applications are alsopresented. A list of relevant references is attached togetherwith our remarks on this subject.

Ching Y. Suen

Papers

Feature selection for ensembles:a hierarchical multi-objective genetic algorithm approach

A generalized knowledge-based system for the recognition of unconstrained handwritten numerals

New Systems and Architectures for Automatic Speech Recognition and Synthesis

KMOD - a new support vector machine kernel with moderate decreasing for pattern recognition. Application to digit image recognition

Analysis and recognition of Asian scripts-the state of the art