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

Social Network Analysis

An Introduction to MultiAgent Systems.

What is modal logic

Usually, a proof of a theorem contains more knowledge than the mere fact that the theorem is true. For instance, to prove that a graph is Hamiltonian it suffices to exhibit a Hamiltonian tour in it; however, this seems to contain more knowledge than the single bit Hamiltonian/non-Hamiltonian.In this paper a computational complexity theory of the “knowledge” contained in a proof is developed. Zero-knowledge proofs are defined as those proofs that convey no additional knowledge other than the correctness of the proposition in question. Examples of zero-knowledge proof systems are given for the languages of quadratic residuosity and 'quadratic nonresiduosity. These are the first examples of zero-knowledge proofs for languages not known to be efficiently recognizable.

/pdf/the-knowledge-complexity-of-interactive-proof-systems-31apre0ecf.pdf

The knowledge complexity of interactive proof-systems

Argumentation mining aims at automatically extracting structured arguments from unstructured textual documents. It has recently become a hot topic also due to its potential in processing information originating from the Web, and in particular from social media, in innovative ways. Recent advances in machine learning methods promise to enable breakthrough applications to social and economic sciences, policy making, and information technology: something that only a few years ago was unthinkable. In this survey article, we introduce argumentation models and methods, review existing systems and applications, and discuss challenges and perspectives of this exciting new research area.

/pdf/argumentation-mining-state-of-the-art-and-emerging-trends-5b2tta8u3k.pdf

Argumentation Mining: State of the Art and Emerging Trends

Attention is an increasingly popular mechanism used in a wide range of neural architectures. The mechanism itself has been realized in a variety of formats. However, because of the fast-paced advances in this domain, a systematic overview of attention is still missing. In this article, we define a unified model for attention architectures in natural language processing, with a focus on those designed to work with vector representations of the textual data. We propose a taxonomy of attention models according to four dimensions: the representation of the input, the compatibility function, the distribution function, and the multiplicity of the input and/or output. We present the examples of how prior information can be exploited in attention models and discuss ongoing research efforts and open challenges in the area, providing the first extensive categorization of the vast body of literature in this exciting domain.

Attention in Natural Language Processing

We continue the work initiated in [1–3], where the acceptance logic, a modal logic for modelling individual and collective acceptances was introduced. This logic is aimed at capturing the concept of acceptance qua member of an institution as the kind of attitude that agents are committed to when they are “functioning as members of an institution”. Acceptance logic can also be used to model judgement aggregation: it deals with how a collective acceptance of the members of an institution about a certain fact φ is created from the individual acceptances of the members of the institution. The contribution of this paper is to present a tableau method for the logic of acceptance. The method automatically decides whether a formula of the logic of acceptance is satisfiable thereby providing an automated reasoning procedure for judgement aggregation in the logic of acceptance.

/pdf/declarative-agent-languages-and-technologies-iv-19ivc6j86j.pdf

Declarative Agent Languages and Technologies IV

SCIFF is a framework thought to specify and verify interaction in open agent societies. The SCIFF language is equipped with a semantics based on abductive logic programming; SCIFF's operational component is a new abductive logic programming proof procedure, also named SCIFF, for reasoning with expectations in dynamic environments. In this article we present the declarative and operational semantics of the SCIFF language, and the termination, soundness, and completeness results of the SCIFF proof procedure, and we demonstrate SCIFF's possible application in the multiagent domain.

Verifiable agent interaction in abductive logic programming: The SCIFF framework

This work presents a formal, logic-based approach to one-to-one agent negotiation, in the context of goal achievement in systems of agents with limited resource availability. The proposed solution is based on agent dialogues as a way, e.g., to request resources and propose resource exchanges. It relies upon agents agreeing solely upon a language for negotiation, while possibly adopting different negotiation policies, each corresponding to an agent variety. Agent dialogues can be connected within sequences, all aimed at achieving an individual agent's goal. Sets of sequences aim at allowing all agents in the system to achieve their goals, and can be used, e.g., to solve the resource reallocation problem. We model dialogues via logic-based dialogue constraints, and propose an execution model to be adopted for the automatic generation of dialogues. We also propose an agent dialogue cycle for the automatic generation of sequences of dialogues. Finally, we identify some desirable properties of dialogues, dialogue sequences and sets of such sequences, and prove/disprove these properties for concrete agent varieties.

Paolo Torroni

Papers

Argumentation Mining: State of the Art and Emerging Trends

Attention in Natural Language Processing

Declarative Agent Languages and Technologies IV

Verifiable agent interaction in abductive logic programming: The SCIFF framework

Dialogues for Negotiation: Agent Varieties and Dialogue Sequences