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

物件導向軟體之架構(Object-Oriented Software Construction)探討

When humans talk with humans, they are able to use implicit situational information, or context, to increase the conversational bandwidth. Unfortunately, this ability to convey ideas does not transfer well to humans interacting with computers. In traditional interactive computing, users have an impoverished mechanism for providing input to computers. By improving the computer’s access to context, we increase the richness of communication in human-computer interaction and make it possible to produce more useful computational services. The use of context is increasingly important in the fields of handheld and ubiquitous computing, where the user?s context is changing rapidly. In this panel, we want to discuss some of the research challenges in understanding context and in developing context-aware applications.

https://www.cc.gatech.edu/fce/ctk/pubs/HUC99-panel.pdf

Towards a Better Understanding of Context and Context-Awareness

Abstract A two-dimensional version of the Pennsylvania State University mesoscale model has been applied to Winter Monsoon Experiment data in order to simulate the diurnally occurring convection observed over the South China Sea. The domain includes a representation of part of Borneo as well as the sea so that the model can simulate the initiation of convection. Also included in the model are parameterizations of mesoscale ice phase and moisture processes and longwave and shortwave radiation with a diurnal cycle. This allows use of the model to test the relative importance of various heating mechanisms to the stratiform cloud deck, which typically occupies several hundred kilometers of the domain. Frank and Cohen's cumulus parameterization scheme is employed to represent vital unresolved vertical transports in the convective area. The major conclusions are: Ice phase processes are important in determining the level of maximum large-scale heating and vertical motion because there is a strong anvil componen...

Numerical study of convection observed during the Winter Monsoon Experiment using a mesoscale two-dimensional model [presentation]

Computing devices and applications are now used beyond the desktop, in diverse environments, and this trend toward ubiquitous computing is accelerating. One challenge that remains in this emerging research field is the ability to enhance the behavior of any application by informing it of the context of its use. By context, we refer to any information that characterizes a situation related to the interaction between humans, applications, and the surrounding environment. Context-aware applications promise richer and easier interaction, but the current state of research in this field is still far removed from that vision. This is due to 3 main problems: (a) the notion of context is still ill defined, (b) there is a lack of conceptual models and methods to help drive the design of context-aware applications, and (c) no tools are available to jump-start the development of context-aware applications. In this anchor article, we address these 3 problems in turn. We first define context, identify categories of contextual information, and characterize context-aware application behavior. Though the full impact of context-aware computing requires understanding very subtle and high-level notions of context, we are focusing our efforts on the pieces of context that can be inferred automatically from sensors in a physical environment. We then present a conceptual framework that separates the acquisition and representation of context from the delivery and reaction to context by a context-aware application. We have built a toolkit, the Context Toolkit, that instantiates this conceptual framework and supports the rapid development of a rich space of context-aware applications. We illustrate the usefulness of the conceptual framework by describing a number of context-aware applications that have been prototyped using the Context Toolkit. We also demonstrate how such a framework can support the investigation of important research challenges in the area of context-aware computing.

/pdf/a-conceptual-framework-and-a-toolkit-for-supporting-the-3ct19ji2mn.pdf

A conceptual framework and a toolkit for supporting the rapid prototyping of context-aware applications

Runtime adaptation mechanisms that leverage software models extend the applicability of model-driven engineering techniques to the runtime environment. Contemporary mission-critical software systems are often expected to safely adapt to changes in their execution environment. Given the critical roles these systems play, it is often inconvenient to take them offline to adapt their functionality. Consequently, these systems are required, when feasible, to adapt their behavior at runtime with little or no human intervention. A promising approach to managing complexity in runtime environments is to develop adaptation mechanisms that leverage software models, referred to as models@run. time. Work on models@run.time seeks to extend the applicability of models produced in model-driven engineering (MDE) approaches to the runtime environment. Models@run. time is a causally connected self-representation of the associated system that emphasizes the structure, behavior, or goals of the system from a problem space perspective.

Models@ run.time

Component-based software structuring principles are now commonplace at the application level; but componentization is far less established when it comes to building low-level systems software. Although there have been pioneering efforts in applying componentization to systems-building, these efforts have tended to target specific application domains (e.g., embedded systems, operating systems, communications systems, programmable networking environments, or middleware platforms). They also tend to be targeted at specific deployment environments (e.g., standard personal computer (PC) environments, network processors, or microcontrollers). The disadvantage of this narrow targeting is that it fails to maximize the genericity and abstraction potential of the component approach. In this article, we argue for the benefits and feasibility of a generic yet tailorable approach to component-based systems-building that offers a uniform programming model that is applicable in a wide range of systems-oriented target domains and deployment environments. The component model, called OpenCom, is supported by a reflective runtime architecture that is itself built from components. After describing OpenCom and evaluating its performance and overhead characteristics, we present and evaluate two case studies of systems we have built using OpenCom technology, thus illustrating its benefits and its general applicability.

https://ftaiani.ouvaton.org/ressources/TOCS.pdf

A generic component model for building systems software

It's flexible and reconfigurable yet simple for programmers to use, notably for building dynamic distributed applications operating on the Net.

The case for reflective middleware

This paper proposes an approach to the design of configurable and open middleware platforms based on the concept of reflection. More specifically, the paper introduces a language-independent reflective architecture featuring a per-object meta-space, the use of meta-models to structure meta-space, and a consistent use of object graphs for composite components. This is complemented by a component framework supporting the construction of meta-spaces. The paper also reports on experiences of implementing the architecture (with emphasis on experiments with open bindings).

/pdf/an-architecture-for-next-generation-middleware-d1ilogr7j9.pdf

An architecture for next generation middleware

Middleware has emerged as an important architectural component in modern distributed systems. Most recently, industry has witnessed the emergence of component-based middleware platforms, such as Enterprise JavaBeans and the CORBA Component Model, aimed at supporting third party development, configuration and subsequent deployment of software. The goal of our research is to extend this work in order to exploit the benefits of component-based approaches within the middleware platform as well as on top of the platform, the result being more configurable and reconfigurable middleware technologies. This is achieved through a marriage of components with reflection, the latter providing the necessary levels of openness to access the underlying component infrastructure. More specifically, the paper describes in detail the OpenCOM component model, a lightweight and efficient component model based on COM. The paper also describes how OpenCOM can be used to construct a full middleware platform, and also investigates the performance of both OpenCOM and this resultant platform. The main overall contribution of the paper is to demonstrate that flexible middleware technologies can be developed without an adverse effect on the performance of resultant systems

/pdf/an-efficient-component-model-for-the-construction-of-3mq3gexhs4.pdf

Gordon S. Blair

Papers

Models@ run.time

A generic component model for building systems software

The case for reflective middleware

An architecture for next generation middleware

An Efficient Component Model for the Construction of Adaptive Middleware