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

How to Do Things With Words

The concept of an agent has become important in both Artificial Intelligence (AI) and mainstream computer science. Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide these issues into three areas (though as the reader will see, the divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents;researchers in this area are primarily concerned with the problem of designing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages may embody principles proposed by theorists. The paper is not intended to serve as a tutorial introduction to all the issues mentioned; we hope instead simply to identify the most important issues, and point to work that elaborates on them. The article includes a short review of current and potential applications of agent technology.

/pdf/intelligent-agents-theory-and-practice-5dchj7p8pc.pdf

Intelligent Agents: Theory and Practice

The present historical moment may seem a particularly inopportune time to review Bowling Alone, Robert Putnam's latest exploration of civic decline in America. After all, the outpouring of volunteerism, solidarity, patriotism, and self-sacrifice displayed by Americans in the wake of the September 11 terrorist attacks appears to fly in the face of Putnam's central argument: that \"social capital\" -defined as \"social networks and the norms of reciprocity and trustworthiness that arise from them\" (p. 19)'has declined to dangerously low levels in America over the last three decades. However, Putnam is not fazed in the least by the recent effusion of solidarity. Quite the contrary, he sees in it the potential to \"reverse what has been a 30to 40-year steady decline in most measures of connectedness or community.\"' As an example of how the current \"war on terrorism\" could generate a durable civic renewal, Putnam points to the burst in civic practices that occurred during and after World War II, which he says \"permanently marked\" the generation that lived through it and had a \"terrific effect on American public life over the last half-century.\" 3 If Americans can follow this example and channel their current civic

Bowling alone: The collapse and revival of American community

Cognition, Joint Action and Collective Intentionality

This paper provides an analysis of the cognitive processes implied in the ego defense known as projection. Projection is first placed in the context of the general cognitive processes of attribution and ascription. Then we address defensive projection, and identify its distinctive features. In particular, whereas general projection consists in the ascription of one's own mental attitudes to others, defensive projection implies one's rejection (via denial or repression) of the ascribed mental states, and ascription is a means for supporting this rejection. We try to understand how and why ascription is functional to rejection. Then, we examine a few types of defensive projection, and identify the main components and steps in the projective process. Finally, we draw some general conclusions.

The Plausibility of Defensive Projection: A Cognitive Analysis

Formalisms based on a propositional representation demonstrate a high representational competence because of their flexibility, properties, and their great expression power, even if they often fail to represent the meaning of the nodes that make up the propositional networks. The presence of a network of definitions would make the representation richer, and would augment the expressiveness and the inferential capabilities of the whole system: the twofold architecture of the hybrid systems seems to be suitable to satisfy these prerequisites. Nevertheless, the hybrid systems fail to clearly define the intensional and extensional levels of knowledge. This paper proposes a different distribution of tasks between the two parts of a hybrid system on the ground of a precise distinction among intensional, mental extensional, and extensional aspects of knowledge. Moreover, it suggests employing a propositional approach also for arranging the abstract definitions of the terminological box. These principles...

Propositional and terminological knowledge representations

The need for coherence of conduct has been viewed, more or less implicitly, as one of the fundamental human needs, in association with one’s social image and self-image. Actually it appears to accomplish a variety of possible functions: identity negotiation, as a condition for smooth and predictable social interactions; the maintenance or enhancement of self-esteem; and the maintenance of one’s self-view regardless of either self-esteem or social identity concerns. In the present work, while acknowledging the plausibility and appeal of such general functions, we will proceed in a more “bottom-up” fashion, trying to single out and analyze in greater detail the possible “uses” of coherence of conduct. We will first specify our notion of coherence of conduct, as well as of its underlying need. Then, we will address its impact on the individual’s behavior, with reference to its relationships with persistence in goal pursuit, the need to show a stable social identity, perceived self-efficacy, general self-esteem, and personal identity or self-image. We will discuss how the need for coherence comes into play in one’s self-image, which includes not only one’s self-evaluations but also, more generally, one’s self-beliefs, especially those about one’s own goals and the kind of person one believes or wants to be. We will focus on the crucial impact of the individual’s values on his or her coherence of conduct. Finally, we will address the issue of self-coherence and change of conduct, pointing to some mechanisms which favor self-coherence without granting actual coherence of conduct. Keywords: coherence of conduct; self-image; persistence; values; defense mechanisms

Coherence of conduct and the self-image

This paper aims to bring together two separate threads in the formal study of epistemic change: belief revision and argumentation theories. Belief revision describes the way in which an agent is supposed to change his own mind , while argumentation deals with persuasive strategies employed to change the mind of other agents . Belief change and argumentation are two sides (cognitive and social) of the same epistemic coin. Argumentation theories are therefore incomplete, if they cannot be grounded in belief revision models - and vice versa. Nonetheless, so far the formal treatment of belief revision widely neglected any systematic comparison with argumentation theories. Such lack of integration poses severe limitations to our understanding of epistemic change, and more comprehensive models should instead be devised. After a short critical review of the literature (cf. 1), we outline an alternative model of belief revision whose main claim is the distinction between data and beliefs (cf. 2), and we discuss in detail its expressivity with respect to argumentation (cf. 3): finally, we summarize our conclusions and future works on the interface between belief revision and argumentation (cf. 4). a b

Cristiano Castelfranchi

Papers

Cognition, Joint Action and Collective Intentionality

The Plausibility of Defensive Projection: A Cognitive Analysis

Propositional and terminological knowledge representations

Coherence of conduct and the self-image

Argumentation and Data-oriented Belief Revision: On the Two-Sided Nature of Epistemic Change