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

The ability of recognizing a multi-agent plan — a plan which has been generated for multiple executing agents — implies the skill of recognizing the plan underlying a collective activity in which a group of agents is involved. Multi-agent plan recognition is a necessary and useful extension of current PR systems in some domains.

Plan Recognition: from Single-Agent to Multi-Agent Plans

Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2

In this (very) extended abstract I will make explicit the general ideological perspective and theoretical claims of the talk (like in a manifesto). As for the exemplification of these claims within the AI domain – in particular within the Agent and Multi-Agent Systems area – I will provide the overall blueprint but I will develop here only some part and give only some examples. I will illustrate how a synthetic paradigm can be built through the notion of different levels of reality description and of scientific theory, and through their interconnections thanks to bridge-theories, cross-layered theories, and layered ontologies. I will provide several examples of bridge-theories and layered ontologies with special attention to agents and multi-agent systems. In particular I will sketch the problem of emotions in agents with reference to agent/mind re-embodiment (the theory of needs and the relation between ‘believing’ and ‘feeling’); I will examine the theory of the mental counterparts of social objects illustrating the mental facet of norms and of commitment; the grounding of social power in the personal power; the cognitive bases of organisations; the layered notions of conflict, cooperation, communication, goal, agent, delegation, as applied to different levels of agenthood.

Emergence and Cognition: Towards a Synthetic Paradigm in AI and Cognitive Science

The possibility of Cooperation is still a matter of debate in the field of GT. Generally speaking, the emergence of cooperation is seen in the prospect of re-encounter as a forward-looking, calculated, and self-interested decision to cooperate. In this paper, it is argued that neither one-shot nor repeated versions of PD-game can account for a theory of cooperation as distinct from other forms of social action, and particularly bargaining it. It is also argued that in order to provide a theory of cooperation it is necessary to ground social interdependence on a general theory of action and planning. More precisely, two theses are presented and discussed: (i) When the PD-game structure is applied to ideal-type situations, one or other of its formal property does not hold. (ii) A plan-based model of social dependence is necessary for disentangling cooperation from other types of social action, especially bargaining: while PD-game applies to the latter, it does not apply to the former! Even in its repeated version, PD-game cannot account for cooperation as distinct from honest bargaining.

The Impossibility of Modelling Cooperation in PD-Game

The future of sensorimotor communication research: Reply to comments on "The body talks: Sensorimotor communication and its brain and kinematic signatures".

Cristiano Castelfranchi

Papers

Plan Recognition: from Single-Agent to Multi-Agent Plans

Proceedings of The 8th International Conference on Autonomous Agents and Multiagent Systems - Volume 2

Emergence and Cognition: Towards a Synthetic Paradigm in AI and Cognitive Science

The Impossibility of Modelling Cooperation in PD-Game

The future of sensorimotor communication research: Reply to comments on "The body talks: Sensorimotor communication and its brain and kinematic signatures".