This work discusses the challenge of developing self-cognisant artificial intelligence systems, looking at the possible benefits and the main issues in this quest. It is argued that the degree of complexity, variation, and specialisation of technological artefacts used nowadays, along with their sheer number, represent an issue that can and should be addressed through an important step towards greater autonomy, that is, the integration of learning, which will allow the artefact to observe its own functionality and build a model of itself. This model can be used to adjust the expectations from an imperfectly manufactured item, patch up its performance and control its consistency over time, so providing a form of self-certification and a warning mechanism in case of deterioration. It is suggested that these goals cannot be fully achieved without the ability of the learner to model its own performance, and the implications and issues of this self-reflective learning are debated. A possible way of quantifying the faculty for self-cognition is proposed, and relevant areas of computer science, philosophy and the study of the evolution of language are mentioned.

1 Neil Audsley 2 Jim Austin 3 Iain Bate 4 Ian Benest 5 Adrian Bors 6 Sam Braunstein 7 Alan Burns 8 Ana Cavalcanti 9 James Cussens 10 Alistair Edwards 11 Edwin Hancock 12 Dimitar Kazakov 13 Gerald Luettgen 14 John McDermid 15 Simon O'Keefe 16 Richard Paige 17 Nick Pears 18 Detlef Plump 19 Fiona Polack 20 Colin Runciman 21 Susan Stepney 22 John Timmis 23 Andy Wellings 24 Richard Wilson 25 Jim Woodcock

In this paper, we describe the Disciplinary Commons project and identify some practical ideas which address central issues for teaching and learning of introductory programming that have emerged from it.

In many cases there is a single interpretation of the verb phrase in question For instance the phrase to provide water for Texas corresponds to parse tree whereas to be the Mayor of Atlanta is an example of tree However sometimes phrases such as to scratch a note on the wall are truly ambiguous wall can be either the medium of the note or the location where the note is written For such examples ambiguity cannot be resolved without the help of the verb phrase context

There are six stages of data mining processes; business understanding, data understanding, data preparation, modelling, evaluation and deployment. The third and one of the most important stages in data mining process is the data cleaning and preparation stage. Data cleaning and pre-processing involve the creation of the relevant data subset through data selection, as well as finding of useful properties/features, generating new features, defining appropriate feature values and/or value discretization. However, data mining's performance and result accuracy highly dependent on the format and the availability of data presented and also the computational data mining tools. Experts are involved in most stages of a data mining project described by the CRISP-DM [Chapman, 2000]. The most informative attributes that influenced the accuracy of data mining are computed prior or during the process of data mining. On the other hand, a complementary approach to such problem solving that does not rely on collecting observational data is decision making. In this approach the human decision maker builds alternative models and defines the preference ordering criteria. This information is then used to make a rational decision. This process can be supported by computational decision support systems. To improve the quality of decision support, better submodels are needed, modeling the underlying decision making processes in a more realistic way. In order to include as much information as possible, the submodels of the expert system are usually provided with a lot of parameters describing different aspects of the decision making, hoping that the characteristics that are truly important are included in the model. In the context of classification, those descriptive parameters are termed features or attributes, and the selection of a good set of features/attributes is of key importance in the design of good classification models that will be used afterwards by the expert system. The roles of experts in data mining and decision supports are different, but complementary [Lavrač and Bohanec, 2003]. In an integrated approach to data mining and decision support, the potential of experts can even better be exploited in all stages of the integrated problem solving process. The gap between the format of data as stored in the data sources and that required by newly developed data mining algorithms must be bridged before any novel machine learning and data modelling algorithms tools can be used to their full potential. Transforming this data into a format appropriate for mining is a key (and often …

A nucleonic device for measuring the moisture content of bulk materials using a radioisotopic fast-neutron source such as lithium-7 admixed with an alpha-particle emitter, such as americium-241, as a means of minimizing the thickness of the layer of bulk material required proximate to the moisture sensor for a neutron-reflection moisture gauge for proper operation of said gauge. Minimization of the required thickness of the bulk material permits use of a neutron-reflection moisture gauge for measurements of bulk materials on lightly-loaded belts and other types of conveyors where measurements have previously been impracticable.

Learning is a crucial ability of intelligent agents. Rather than presenting a complete literature review, we focus in this paper on important issues surrounding the application of machine learning (ML) techniques to agents and multi-agent systems (MAS). In this discussion we move from disembodied ML over single-agent learning to full multi-agent learning. In the second part of the paper we focus on the application of Inductive Logic Programming, a knowledge-based ML technique, to MAS, and present an implemented framework in which multi-agent learning experiments can be carried out.

The initial section tries to give reasons why to communicate with robots making-use of a natural language. The subject of the paper deals with a design and the art of possible cooperation between a spoken interface module (SIM) and a symbolic model of the robot environment. Attached case-study describing our approach how to couple a SIM to a symbolic world model is targeted on experiments with the mobile robot developed in The Gerstner Laboratory.

European research in Inductive Logic Programming (ILP) has been mainly conducted within two ESPRIT research projects, ILP (1992-95) and ILP2 (1996-98), whereas the European Inductive Logic Programming Scientific Network ILPNET (1993-96) provided the infrastructure support for ILP research. The main results of ILPNET are outlined in this paper. Particular emphasis is given on the description of ILPNET repositories of ILP systems, datasets and bibliography, which have been made publicly available on WWW at http://www-ai.ijs. si/ilpnet.html.