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

Much attention has been recently given to VLSI and WSI processing arrays: systolic arrays are often adopted to execute a wide class of algorithms, e.g for matrix arithmetic or signal and image processing. In this paper a fault-tolerant architecture is proposed to allow reliable computation of systolic arrays by using physical redundancy and residue number coding. Such architecture supplies also information for fast reconfiguration.

Fault-tolerant systolic arrays: An approach based upon residue arithmetic

The modeling of solar radiation for forecasting its availability is a key tool for managing photovoltaic (PV) plants and, hence, is of primary importance for energy production in a smart grid scenario. However, the variability of the weather phenomena is an unavoidable obstacle in the prediction of the energy produced by the solar radiation conversion. The use of the data collected in the past can be useful to capture the daily and seasonal variability, while measurement of the recent past can be exploited to provide a short term prediction. It is well known that a good measurement of the solar radiation requires not only a high class radiometer but even a correct management of the instrument. In order to reduce the cost related to the management of the monitoring apparatus, a solution could be to evaluate the PV plant performance using data collected by public weather station installed near the plant. In this paper, two computational intelligence models are challenged; two different ground global horizontal radiation dataset have been used: the first one is based on the data collected by a public weather station located in a site different to that one of the plant, the second one, used to validate the results, is based on data collected by a local station.

/pdf/computational-intelligence-models-for-solar-radiation-4reiu7byfl.pdf

Computational intelligence models for solar radiation prediction

Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR), most algorithms of which have employed and relied on sufficient training samples to receive a strong discriminative classification model, has remained a challenging task in recent years, among which the challenge of SAR data acquisition and further insight into the intuitive features of SAR images are the main concerns. In this paper, a deep transferred multi-level feature fusion attention network with dual optimized loss, called a multi-level feature attention Synthetic Aperture Radar network (MFFA-SARNET), is proposed to settle the problem of small samples in SAR ATR tasks. Firstly, a multi-level feature attention (MFFA) network is established to learn more discriminative features from SAR images with a fusion method, followed by alleviating the impact of background features on images with the following attention module that focuses more on the target features. Secondly, a novel dual optimized loss is incorporated to further optimize the classification network, which enhances the robust and discriminative learning power of features. Thirdly, transfer learning is utilized to validate the variances and small-sample classification tasks. Extensive experiments conducted on a public database with three different configurations consistently demonstrate the effectiveness of our proposed network, and the significant improvements yielded to surpass those of the state-of-the-art methods under small-sample conditions.

MFFA-SARNET: Deep Transferred Multi-Level Feature Fusion Attention Network with Dual Optimized Loss for Small-Sample SAR ATR

Real-time monitoring of the laser-based applications is becoming a main issue for quality analysis in the steel manufacturing industry. The paper suggests a solution achieving an automated real-time quality inspection in laser welding applications. A composite system composed of soft computing and traditional techniques has been considered for its positive impact on the reduced computation compared with more traditional approaches.

/pdf/composite-techniques-for-quality-analysis-in-automotive-1sbjsudld2.pdf

Composite techniques for quality analysis in automotive laser welding

The computational needs of an increasing number of applications often require dedicated circuits. Configurable devices, like the Field-Programmable Gate Arrays (FPGAs), are one of the most used solutions to implement such a hardware support. However the size of the circuits that can be mapped on the currently available FPGAs at a medium or low cost is limited with respect to the high demand of several applications in particular when embedded systems and single-chip systems are concerned. This paper introduces some operating-system techniques (namely, partitioning and overlaying) to virtually enlarge the size of the FPGA from the point of view of the applications. The solutions mimic the approaches widely used in the operating systems for virtual memory.

Vincenzo Piuri

Papers

Fault-tolerant systolic arrays: An approach based upon residue arithmetic

Computational intelligence models for solar radiation prediction

MFFA-SARNET: Deep Transferred Multi-Level Feature Fusion Attention Network with Dual Optimized Loss for Small-Sample SAR ATR

Composite techniques for quality analysis in automotive laser welding

General methodologies to virtualize FPGAs in Hw/Sw systems