From the Publisher: 
The accessible presentation of this book gives both a general view of the entire computer vision enterprise and also offers sufficient detail to be able to build useful applications. Users learn techniques that have proven to be useful by first-hand experience and a wide range of mathematical methods. A CD-ROM with every copy of the text contains source code for programming practice, color images, and illustrative movies. Comprehensive and up-to-date, this book includes essential topics that either reflect practical significance or are of theoretical importance. Topics are discussed in substantial and increasing depth. Application surveys describe numerous important application areas such as image based rendering and digital libraries. Many important algorithms broken down and illustrated in pseudo code. Appropriate for use by engineers as a comprehensive reference to the computer vision enterprise.

Computer vision : a modern approach = 计算机视觉 : 一种现代的方法

An overview of the self-organizing map algorithm, on which the papers in this issue are based, is presented in this article.

The Self-Organizing Map

Fast Fourier Transform

Computer algebra systems are now ubiquitous in all areas of science and engineering. This highly successful textbook, widely regarded as the “bible of computer algebra”, gives a thorough introduction to the algorithmic basis of the mathematical engine in computer algebra systems. Designed to accompany oneor two-semester courses for advanced undergraduate or graduate students in computer science or mathematics, its comprehensiveness and reliability has also made it an essential reference for professionals in the area. Special features include: detailed study of algorithms including time analysis; implementation reports on several topics; complete proofs of the mathematical underpinnings; and a wide variety of applications (among others, in chemistry, coding theory, cryptography, computational logic, and the design of calendars and musical scales). A great deal of historical information and illustration enlivens the text. In this third edition, errors have been corrected and much of the Fast Euclidean Algorithm chapter has been renovated.

Modern computer algebra

The Artificial Intelligence field continues to be plagued by what can only be described as ‘bold promises for the future syndrome’, often perpetrated by researchers who should know better. While impartial assessment can point to concrete contributions over the past 50 years (such as automated theorem proving, games strategies, the LISP and Prolog high-level computer languages, Automatic Speech Recognition, Natural Language Processing, mobile robot path planning, unmanned vehicles, humanoid robots, data mining, and more), the more cynical argue that AI has witnessed more than its fair share of ‘unmitigated disasters’ during this time – see, for example [3,58,107,125,186]. The general public becomes rapidly jaded with such ‘bold predictions’ that fail to live up to their original hype, and which ultimately render the zealots’ promises as counter-productive.

Computational Intelligence: An Introduction

A framework for implementing network protocols on multiprocessor SoCs has been described. This chapter also shows how to model network protocol and hardware architecture, how to schedule the execution to guarantee a user-defined throughput per port, how to assign protocol functions to processors, and how to estimate resource consumption of the final mapping with a component-based estimation model. The methods can be applied in an early design phase and can be used to explore the design space created by different system parameters. A detailed exploration example is presented to show how a medium access protocol for mobile ad hoc networks can be mapped to a multiprocessor SoC with up to 64 processors. The analysis shows that such a system can achieve reasonable data rates for examined application at low power consumption. This methodology can also be used to quickly identify the bottlenecks of the system such as protocol functions whose computational complexity prevents a higher throughput. The framework cannot yet handle external memories. A possible way to include them is to add memory interfaces to border PEs and to form groups of border PEs that share one memory channel. The external memory can be used to store large data structures such as packet queues or filter tables. By knowing the access pattern of the packet methods and the contention resolution mechanism on shared memory channel, worst-case memory access times can be determined analytically. Hence, the influence of the external memory accesses on the execution time of the packet methods can be modeled and included in the scheduling scheme.

A framework for design space exploration of resource efficient network processing on multiprocessor SoCs

In recent years there has been an increasing interest in the use of artificial neural networks (ANNs) for technical applications (e.g. Rogers 1990). Particularly attractive is the application of ANNs in those domains where at present humans outperform any currently available high performance computers, e.g. in areas like auditory perception, vision, or sensory-motor control. Neural information processing is expected to have a wide applicability in areas that require a high degree of flexibility and the ability to operate in uncertain environments where information usually is partial, fuzzy, or even contradictory. The computing power of biological neural networks stems to a large extend from a highly parallel, fine-grained and distributed processing and storage of information as well as from the capability of learning.

Knowledge processing in neural architecture

Neural networks are intended to be used in future nanoelectronics since these architectures seem to be fault-tolerant to malfunctioning elements and robust to noise. In this paper, the robustness to noise of basis function networks using tensor product stabilizers is analyzed and upper bounds of the mean square error under noise contaminated weights or inputs are determined. Furthermore, consequences of permanently malfunctioning neurons are investigated and their impact on the mean squared error is analyzed. To achieve a reliable operation of the neural network necessary restrictions are introduced. Finally, the impact of technical realizations is investigated and its complexity is compared to radial basis functions.

Fault-tolerance of basis function networks using tensor product stabilizers

An example of a hybrid system architecture integrating connectionist models and symbolic knowledge processing is introduced. In particular the inclusion of non-symbolic knowledge sources (data from physical processes, measurements, sensors etc.), transformation of learned knowledge into a symbolic form (rule extraction) and associative storage as well as retrieval of information are discussed by means of application examples. Finally, parallel hardware support for the proposed hybrid system architecture is presented.

/pdf/a-hybrid-knowledge-processing-architecture-2cpougx99h.pdf

A hybrid knowledge processing architecture

In the field of explorative data analysis self-organizing maps have been used successfully for a lot of applications. In our case, we apply the self-organizing map for the analysis of semiconductor fabrication data by training recorded high dimensional data sets. Usually, the training result is displayed by using appropriate visualization techniques and the results are evaluated manually. Especially for large data sets an automated post-processing of the training result is essential. In this paper an automatic training result analysis based on specific image processing is introduced. Dependencies between components maps are calculated by structure overlapping analysis based on the segmentation of component maps. This novel method has been integrated into the data analysis software DanI, that simulates self-organizing maps for data analysis with several pre-processing and post-processing capabilities.

/pdf/explorative-data-analysis-based-on-self-organizing-maps-and-3rqkmytfj9.pdf

Ulrich Rückert

Papers

A framework for design space exploration of resource efficient network processing on multiprocessor SoCs

Knowledge processing in neural architecture

Fault-tolerance of basis function networks using tensor product stabilizers

A hybrid knowledge processing architecture

Explorative data analysis based on self-organizing maps and automatic map analysis