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

This chapter introduces knowledge processing and decision making using agent-based technologies. The importance of creating effective and efficient computerized systems for extracting information and processing knowledge as well as for supporting decision making activities is highlighted. Then, an overview covering agent-based software tools and development methodologies, and usability and challenges of agent-based systems in industrial applications is presented. The contribution of each chapter included in this book is also described.

Innovations in Knowledge Processing and Decision Making in Agent-Based Systems

The aim of this research is to equip agents in a Multi-Agent System (MAS) with reusable autonomous capabilities to enable them to behave in unknown situations and complex simulated environments. A concept demonstrator called Web-based Multi-Agent System Testbed (Web-MAT) is developed with a context switchable capability currently implemented as a Real-Time Strategy (RTS) game. The demonstrator is intended to enable researchers to improve/develop the communication aspects within an agent-oriented architecture and to program agents that automatically adapt functionality at runtime using event stimuli. Complementary research on a variety of agent tools (specifically JACK, JADE and CIAgent) and communication languages (ACL, KQML, FIPA and SOAP) has been reviewed to glean knowledge that enables these agents to adapt into Web-MAT and generate encouraging results.

Web-based multi-agent system architecture in a dynamic environment

Safety onboard airborne platforms rests heavily on the way they are fixed. This fact includes repairs and testing, to reduce its down time. Maintenance practices using these components are achieved using generic and specific test equipment within the existing Maintenance Management System (MMS). This research paper reports the work performed to improve reliability and maintainability of Avionics Systems using an Intelligent Decision Support System (IDSS). In order to understand the shortcomings of the existing system, the prevalent practices and methodologies are researched. The paper reports the significant improvements made by integrating autonomous information sources as knowledge into an IDSS. Improvements are made by automating the existing data collection to create an expert system using intelligent agents. Data Mining techniques and intelligent agents are employed to create an expert system. Using feedback, the IDSS generates forecasts, alerts and warnings prior to system availability being compromised. If the data was stored electronically, Data Mining techniques and intelligent agents could be employed to create an expert system. Using feedback, an IDSS should generate forecasts or warnings prior to system availability being compromised. A Knowledge Base of all aspects of the logistics cycle is created as the system ages, to help make informed decisions about the platform, the Unit Under Test (UUT) or even the environment that supports it.

An Intelligent Decision Support System Using Expert Systems in a MAS

Normally an intelligent decision support system is build to solve complex problems involving multi-criteria decisions. The knowledgebase is the vital part of the decision support system containing the knowledge or data that is used for decision-making. Several works have been done where engineers and scientists have applied intelligent techniques and heuristics to obtain optimal decisions from imprecise information. In this paper, we present a hybrid neuro-fuzzy technique for the adaptive learning of Takagi-Sugeno type fuzzy if-then rules for the Tactical Air Combat Decision Support System (TACDSS). Experiment results clearly demonstrate the efficiency of the proposed technique. Some simulation results demonstrating the difficulties to decide the optimal number and shape of the membership functions are also provided.

TACDSS: Adaptation Using a Hybrid Neuro-Fuzzy System

Like standard discrete artificial neural networks (ANNs), continual neurodynamical systems can be used for the classification and diagnosis of breast cancer. In this paper, a two-feature generalized bidirectional associative memory (GBAM) classifier is formulated in tensorial invariant form. It is implemented in Mathematica 3.0 and tested on two sample features (the radius and perimeter of cell nuclei in fine-needle aspiration slides) from the Wisconsin breast-cancer database. The classification accuracy obtained (86%), together with the invariance of the classification result upon the variation of the dimensions and output form of the neural activation fields, shows the potential classification ability of theoretical classifiers that are directly implemented in computer algebra systems.

Lakhmi C. Jain

Papers

Innovations in Knowledge Processing and Decision Making in Agent-Based Systems

Web-based multi-agent system architecture in a dynamic environment

An Intelligent Decision Support System Using Expert Systems in a MAS

TACDSS: Adaptation Using a Hybrid Neuro-Fuzzy System

A new two-feature GBAM-neurodynamical classifier for breast cancer diagnosis