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

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

Data Mining Practical Machine Learning Tools and Techniques

How has Japan become a major economic power, a world leader in the automotive and electronics industries? What is the secret of their success? The consensus has been that, though the Japanese are not particularly innovative, they are exceptionally skilful at imitation, at improving products that already exist. But now two leading Japanese business experts, Ikujiro Nonaka and Hiro Takeuchi, turn this conventional wisdom on its head: Japanese firms are successful, they contend, precisely because they are innovative, because they create new knowledge and use it to produce successful products and technologies. Examining case studies drawn from such firms as Honda, Canon, Matsushita, NEC, 3M, GE, and the U.S. Marines, this book reveals how Japanese companies translate tacit to explicit knowledge and use it to produce new processes, products, and services.

The knowledge-creating company : how Japanese companies create the dynamics of innovation

How to Do Things With Words

Kernel based Fuzzy Clustering

Started in 1997, the International Conference on Knowledge-Based and Intelligent Information & Engineering Systems (KES) series of conference provides excellent opportunities for the presentation of new, interesting research findings and results in the general areas of knowledge-based and intelligent systems, leading to knowledge transfer and the generation of new ideas and techniques in engineering and information technology. KES2008 is the 12th KES conference organized by the University of Zagreb and its Faculty of Electrical Engineering and Computing in association with KES International (http://www.kesinternational.org/). The KES2008 conference took place in Zagreb, the capital of the Republic of Croatia, from 3–5 September, 2008. The KES 2008 conference featured keynote lectures by distinguished researchers in their fields, invited sessions organized and chaired by respected experts in specialized areas, as well as general sessions managed by track chairs. After a careful review process, a total of 316 high-quality papers have been accepted for poster and oral presentation. Three volumes of the conference proceedings have been compiled and published as Lecture Notes in Artificial Intelligence by Springer. This special issue contains four carefully selected papers from the KES2008 conference. The papers address theoretical advances as well as practical applications of intelligent knowledge processing and decision

Guest-editorial: special issue on intelligent knowledge processing and decision making techniques

This volume contains the Proceedings of the 4th International Conference on Intelligent Interactive Multimedia Systems and Services (IIMSS-2011). IIMSS-2011 comes as a sequel to IIMSS-2008 (Piraeus-Athens, Greece, July 9, 10 and 11, 2008), IIMSS-2009 (Mogliano Veneto (near Venice), Italy, July 15, 16 and 17, 2009) and IIMSS-2010 (Baltimore, USA, July 28, 29, and 30, 2010). This fourth edition of the IIMSS Conference was organized jointly by the Department of Informatics of the University of Piraeus, Greece and the School of Electrical and Information Engineering of the University of South Australia, in conjunction with KES International.At a time when computers are more widespread than ever and computer users range from highly qualified scientists to non-computer-expert professionals and may include people with special needs, interactivity, personalization and adaptivity have become a necessity in modern multimedia systems. Modern intelligent multimedia systems need to be interactive not only through classical modes of interaction where the user inputs information through a keyboard or mouse. They must also support other modes of interaction, such as visual or lingual computer-user interfaces, which render them more attractive, user friendlier, more human-like and more informative. IIMSS is a new series of international scientific conferences aimed at presenting novel research in the fields of intelligent multimedia systems relevant to the development of a new generation of interactive, user-centric services.

Intelligent Interactive Multimedia Systems and Services: Proceedings of the 4th International Conference on Intelligent Interactive Multimedia Systems

Presents one of the software packages that we are developing for teaching electricity and electronics, the first-year subject that is common to all engineering students. This package is developed with the aim of guiding the user in developing laboratory experiments and preparing students to perform real experiments in the laboratory. The package itself represents a library of templates which is needed to develop a laboratory experiment, including a more general set of templates related to the particular engineering field and a more specific set of templates related to the particular experiment. The package also includes a set of exemplary experiments developed for the above-mentioned first-year subject The package is now in the development stage, and in this paper we presents some of the ideas that are being used to solve the problems that were faced.

Multimedia package for interactive design of laboratory experiments (LabCAD)

For the past 20 years, BDI (Belief, Desire, Intention) frameworks such as PRS [1], dMARS [2] and JACK [3] have provided, together with Soar [4], the two environments of choice for the development of knowledge rich, industrial strength intelligent agent applications [5]. However, we have observed that while the BDI model of plan execution works well for the tactical reasoning component of such applications, operational reasoning often requires a richer execution model. In this paper, we present an alternative, but complementary model for plan step execution by BDI agents. In the BDI model, plan steps either succeed or fail; if a plan step fails, then the plan fails and reconsideration of the current goal may occur. We have found that this approach is problematic when used for applications where resource contention is a regular occurrence, such as in manufacturing execution [6]. In these situations, it is necessary to review progress after each step, regardless of the step outcome. Our alternative model for plan step execution allows for the explicit modelling of the plan step lifecycle and the utilisation of infrastructure to manage the progression of that lifecycle. The model is realised using the JACK™ Intelligent Agents (JACK) product suite [3] and its feasibility is demonstrated through the development of an execution system for a robotic assembly cell.

Lakhmi C. Jain

Papers

Kernel based Fuzzy Clustering

Guest-editorial: special issue on intelligent knowledge processing and decision making techniques

Intelligent Interactive Multimedia Systems and Services: Proceedings of the 4th International Conference on Intelligent Interactive Multimedia Systems

Multimedia package for interactive design of laboratory experiments (LabCAD)

A flexible plan step execution model for BDI agents