Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

An Introduction to MultiAgent Systems.

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

International Technology Roadmap for Semiconductors 2003の要求清浄度について － シリコンウエハ表面と雰囲気環境に要求される清浄度, 分析方法の現状について －

This chapter introduces the subject of statistical pattern recognition (SPR). It starts by considering how features are defined and emphasizes that the nearest neighbor algorithm achieves error rates comparable with those of an ideal Bayes’ classifier. The concepts of an optimal number of features, representativeness of the training data, and the need to avoid overfitting to the training data are stressed. The chapter shows that methods such as the support vector machine and artificial neural networks are subject to these same training limitations, although each has its advantages. For neural networks, the multilayer perceptron architecture and back-propagation algorithm are described. The chapter distinguishes between supervised and unsupervised learning, demonstrating the advantages of the latter and showing how methods such as clustering and principal components analysis fit into the SPR framework. The chapter also defines the receiver operating characteristic, which allows an optimum balance between false positives and false negatives to be achieved.

Statistical Pattern Recognition

Recent advances in FPGA technologies allow to configure the RAM-based FPGA devices in a reduced time as an effective support for real-time applications. The physical dimensions of FPGAs (pinout and gate count) limit the complexity of circuits that can be implemented. In many applications, very large circuits should be realized without requiring either a very large FPGA or many FPGAs; in some real-time systems as well as in multitasking and time-shared environments, it could be valuable to change dynamically the implemented circuit so as to support different applications competing for the FPGA resource. This paper introduces and discusses the concept of Virtual FPGA as an extension of the physical FPGA device: applications have a virtual view of the FPGA that is then mapped on the available physical device by the operating system, in a way similar to the virtual memory.

Virtual FPGAs: Some steps behind the physical barriers

The use of artificial intelligence techniques introduces a new set of problems related to the characterization of the new instrumentation and measurement procedures, incorporating some components based on these instrumentation-processing technologies. Research is needed to define and evaluate suitable methodologies and techniques in order to identify and specify the accuracy, the precision, and the confidence of the measurements performed by using these advanced instrumentation and measurement procedures, in particular with respect to the algorithmic choices embedded in the related software and the computing system itself. For the near future, these are the challenges of the research communities in the areas of instrumentation and measurement as well as in computer science and engineering.

Artificial intelligence for instruments and measurement applications

Computer Aided Diagnosis (CAD) systems are increasingly utilizing image analysis and Deep Learning (DL) techniques, due to their high accuracy in several medical imaging fields, including the detection of Acute Lymphoblastic (or Lymphocytic) Leukemia (ALL) from peripheral blood samples. However, no method in the literature has specifically analyzed the focus quality of ALL images or proposed a technique for sharpening the samples in an adaptive way for the purpose of classification. To address this issue, in this paper we propose the first machine learning-based approach able to enhance blood sample images by an adaptive unsharpening method. The method uses image processing techniques and DL to normalize the radius of the cell, estimate the focus quality, adaptively improve the sharpness of the images, and then perform the classification. We evaluated the methodology on a public database of ALL images, considering several state-of-the-art CNNs to perform the classification, with results showing the validity of the proposed approach. For a complete reproducibility of the work, the source code is available at: http://iebil.di.unimi.it/cnnALL/index.htm.

/pdf/acute-lymphoblastic-leukemia-detection-based-on-adaptive-3xm2w8u5sa.pdf

Acute Lymphoblastic Leukemia Detection Based on Adaptive Unsharpening and Deep Learning

Efficient implementation of neural networks requires high-performance architectures, while VLSI realization for mission-critical applications must include fault tolerance. Contemporaneous solution of such problems has not yet been completely afforded in the literature. This paper focuses both on data representation to support high-performance neural computation and on error detection to provide the basic information for fault tolerance by using the redundant binary representation with a three-rail logic implementation. Costs and performances are evaluated referring to multilayered feed-forward networks.

High performance fault-tolerant digital neural networks

Iris-based biometric systems identify individuals by comparing the characteristics of the iris captured by suited sensors. When reflections are present in the iris image, the portion of the iris covered by the reflections should not be considered in the comparison since it may produce erroneous matches. This paper presents an adaptive design methodology for reflection detection and location in iris biometric images based on inductive classifiers, such as neural networks. In particular, this paper proposes a set of features that can be extracted and measured from the iris image and that can effectively be used to achieve an accurate identification of the reflection position using a trained classifier. In addition, the use of radial symmetry transform (RST) is presented to identify the reflections in iris images. The proposed design methodology is general and can be used in any biometric system based on iris images.

Vincenzo Piuri

Papers

Virtual FPGAs: Some steps behind the physical barriers

Artificial intelligence for instruments and measurement applications

Acute Lymphoblastic Leukemia Detection Based on Adaptive Unsharpening and Deep Learning

High performance fault-tolerant digital neural networks

Adaptive Reflection Detection and Location in Iris Biometric Images by Using Computational Intelligence Techniques