Blind Image Deconvolution Via Dispersion Minimization

Blind Image Deconvolution Via Dispersion Minimization

Blind Equalization in Neural Networks

The book begins with an introduction of blind equalization theory and its application in neural networks, then discusses the algorithms in recurrent networks, fuzzy networks and other frequently-studied neural networks. Each algorithm is accompanied by derivation, modeling and simulation, making the book an essential reference for electrical engineers, computer intelligence researchers and neural scientists.

Opportunities and Challenges for Next-Generation Applied Intelligence

The term “Artificial Intelligence” has been used since 1956 and has become a very popular research field. Generally, it is the study of the computations that enable a system to perceive, reason and act. In the early days, it was expected to achieve the same intelligent behavior as a human, but found impossible at last. Its goal was thus revised to design and use of intelligent methods to make systems more ef- cient at solving problems. The term “Applied Intelligence” was thus created to represent its practicality. It emphasizes applications of applied intelligent systems to solve real-life problems in all areas including engineering, science, industry, automation, robotics, business, finance, medicine, bio-medicine, bio-informatics, cyberspace, and man-machine interactions. To endow the intelligent behavior of a system, many useful and interesting techniques have been developed. Some of them are even borrowed from the na- ral observation and biological phenomenon. Neural networks and evolutionary computation are two examples of them. Besides, some other heuristic approaches like data mining, adaptive control, intelligent manufacturing, autonomous agents, bio-informatics, reasoning, computer vision, decision support systems, expert s- tems, fuzzy logic, robots, intelligent interfaces, internet technology, planning and scheduling, are also commonly used in applied intelligence.