Learning other agents' preferences in multiagent negotiation

In multiagent systems, an agent does not usually have complete information about the preferences and decision making processes of other agents. This might prevent the agents from making coordinated choices, purely due to their ignorance of what others want. This paper describes the integration of a learning module into a communication-intensive negotiating agent architecture. The learning module gives the agents the ability to learn about other agents' preferences via past interactions. Over time, the agents can incrementally update their models of other agents' preferences and use them to make better coordinated decisions. Combining both communication and learning, as two complement knowledge acquisition methods, helps to reduce the amount of communication needed on average, and is justified in situations where communication is computationally costly or simply not desirable (e.g. to preserve the individual privacy).

Narrative structure analysis with education and training videos for e-learning

This paper deals with the problem ofstructuralizing education and training videos for high-level semantics extraction and nonlinear media presentation in e-learning applications. Drawing guidance from production knowledge in instructional media, we propose six main narrative structures employed in education and training videos for both motivation and demonstration during learning and practical training. We devise a powerful audiovisual feature set, accompanied by a hierarchical decision tree-based classification system to determine and discriminate between these structures. Based on a two-liered hierarchical model, we demonstrate that we can achieve an accuracy of 84.7% on a comprehensive set of education and training video data.

A framework for co-ordination and learning among teams of agents

We present a framework for team coordination under incomplete information based on the theory of incomplete information games. When the true distribution of the uncertainty involved is not known in advance, we consider a repeated interaction scenario and show that the agents can learn to estimate this distribution and share their estimations with one another. Over time, as the set of agents' estimations become more accurate, the utility they can achieve approaches the optimal utility when the true distribution is known, while the communication requirement for exchanging the estimations among the agents can be kept to a minimal level.

A hybrid ART-GRNN online learning neural network with a ε-insensitive loss function

In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.

Techno-literacy and learning in blended, multicultural course environments

For the last two decades, higher education institutions have been actively engaged in the use of online technology with the aim of transforming the way we teach and learn to improve students’ learning experiences and outcomes. However, despite significant investment in infrastructure and training and a wide-scale uptake of such technologies, the promised transformative effect on student learning is yet to be actualised outside of small pockets of innovation. In this paper, we argue that one of the factors contributing to lack of qualitative large-scale transformation is students’ lack of preparedness and experience in using online tools for learning purposes. Drawing on an ethnographic study of culturally diverse computing students and teachers within learning environments that blend online and face-to-face pedagogies, we argue that, although contemporary university students are largely operationally literate when using online learning tools, they often lack the cultural and critical skills required to use such technologies in a meaningful way to support powerful learning. We argue that, for online learning technologies to transform learning, students need to be supported to develop these higher order techno-literacy skills.

Managing manufacturing technology investments: An intelligent learning system approach

This paper proposes an intelligent decision-support system for managing manufacturing technology investments. The intelligent system is a hybrid integration of two information processing modules: case-based reasoning and fuzzy ARTMAP – a supervised adaptive resonance theory (ART) neural network with a multi-dimensional map. The developed system captures a company's strategic information, provides facilities to quantify qualitative attributes and analyses them alongside the quantitative attributes in an evaluation framework. Through the system, similar cases can be retrieved to enable managers to make effective use of their knowledge and experience of previously delivered technologies and projects as an input to the prioritization of future projects. Other salient features of the system include its ability to adapt and absorb new knowledge and responses pertaining to significant events in the business environment, as well as to extract and elucidate information from the knowledge database for explaining and justifying its analysis. The applicability of the developed system is evaluated using a real case study in collaboration with a pharmaceutical manufacturing firm.

Engagement and learning through social software in finance : a retrospective on the Trading Room experience

The introduction of a social software blog space called the Trading Room in an undergraduate finance unit generated a great deal of activity to support student learning. A subsequent evaluation of this innovation, viewed through the lens of Activity Theory, demonstrated that students perceived high value in the opportunity it provided for them to reaffirm theories, obtain individualised feedback and benchmark their work against others. While assessment is generally seen as the carrot and the stick of learning; students in the study reported that they would still participate in reading and posting to the Trading Room even if there was no assessment requirement. Students did not see any value in the environment as a purely social space, reporting that they saw it primarily as a professional educational community. It would appear that just as there are different communities in the real world social space, there are also different types of communities in the online space.

Feeding back and enhancing authentic learning in quality course assessment design : locating information systems education in rigorous educational research

Locating information systems education foursquare within rigorous and substantial educational research is crucial if the discipline is to receive the scholarly attention that it warrants. One way to do that is to highlight how current information systems course design in Australian undergraduate and postgraduate programs exhibits the strongest possible elements of contemporary learning theories. This paper analyses selected features of the design of an information systems postgraduate course in an Australian university, including the use of peer review of journal entries and writing professional reports to enhance authentic learning and maximise quality assessment design. The analysis is framed by the principles of instructional design theory (Snyder 2009). The authors argue that, by demonstrating theoretically grounded and effective educational practice, the course highlights the value of being located in wider educational research, and of bringing the two fields more closely together.

Putting the cog into cognitive : the theory behind teaching practice.

During teacher education programs, lecturers introduce students to the joys of studying a range of theorists. Sadly, many teachers appear to put theoretical perspectives of practice behind them immediately the essay-writing is over. The purpose of this paper is to breathe life into the work of theorist, relevant to early childhood teaching. I aim to inspire teachers to gain a new depth of satisfaction from their teaching as they critically reflect on their practice and gain a deeper understanding of teaching strategies that support children’s learning and development.

Learning to become an academic

This chapter explores the informal learning dimensions of ‘learning to become an academic’. I explore in detail the process of becoming a scholar with particular emphasis given to the supervisory relationship as a process of apprenticeship and learning community. My Ph.D. focussed on the informal and social learning practices of two groups of activists, so this paper also covers the journey of the research, the methodology and the methods chosen for the research. I outline the early corporeal learning experiences that constituted my own educational experience as a young woman growing up working class, who turned to ideas and theory for a language of resistance to educational discourses about class. This paper has a particular focus on the role of ‘identity’ formation in learning to become an academic. I outline the processes of apprenticeship through supervision and the role of a learning community in the Ph.D., as key in developing ‘mastery’ or a ‘feel for the game’ of academia.

Learning architecture through ideas about the spatial body

There are many varied ways that the human body is referred to in the thinking about architecture. However, rethinking about the body in other disciplines has meant that some of the binary theories within architecture have needed to be reviewed. The spatial body is a particular conceptualisation of the body that brings a focus onto space within architecture, and proposes that rethinking space through the body produces different and new ideas of spatiality. This paper examines body-architecture relations and how they might be revised in order that a spatial body is conceptualised. While this idea of the spatial body has been theorised through research, it can also be explored through creative practices and teaching. The theory is extended by a presentation of a studio programme that tried to develop exploration of architectural space through the idea of the spatial body.

Learning to engage with human rights in heritage

Cultural heritage should not be seen merely as a technical matter or from a narrow visitor management point of view but rather as cultural practice—a form of cultural politics dominated by ruling regimes and social groups in which decisions are made about the future of and access to scarce resources. Several scholars have sought to push this approach further by arguing that heritage studies should take on the protection of human rights as a core consideration in the processes of identifying, inscribing, conserving and interpreting cultural heritage. This paper builds on these previous works to explore what the shift to a rights-based management approach in the World Heritage system might mean for various stakeholders in the heritage protection enterprise as they learn to meet this challenge and to find ways to support people’s right to access, enjoy and maintain cultural heritage. Reaffirming the need to maintain a strong relationship between theory and praxis, the paper draws into the discussion heritage practitioners, decision makers in governments and government agencies, scholars and educators. Of these, the principal emphasis in this paper is on educators who are seen to have a fundamentally important role in developing a critical understanding of the cultural heritage concept, how heritage is created, used and misused and how conservation approaches and programs sit within the broader context of community attitudes and aspirations and governmental responsibilities. A distinction is made between teachers in universities and trainers offering short courses more focused on specific employer needs. The paper focuses on World Heritage but refers to both tangible and intangible aspects. It shows how current moves to establish a rights-based approach to the management of World Heritage sites connects with moves elsewhere in global governance, most notably in the United Nations Permanent Forum on Indigenous Issues and the United Nations Human Rights Commission.

Mind change efficient learning

This paper studies efficient learning with respect to mind changes. Our starting point is the idea that a learner that is efficient with respect to mind changes minimizes mind changes not only globally in the entire learning problem, but also locally in subproblems after receiving some evidence. Formalizing this idea leads to the notion of uniform mind change optimality. We characterize the structure of language classes that can be identified with at most α mind changes by some learner (not necessarily effective): A language class L is identifiable with α mind changes iff the accumulation order of L is at most α. Accumulation order is a classic concept from point-set topology. To aid the construction of learning algorithms, we show that the characteristic property of uniformly mind change optimal learners is that they output conjectures (languages) with maximal accumulation order. We illustrate the theory by describing mind change optimal learners for various problems such as identifying linear subspaces and one-variable patterns.

Learning in social action : the informal and social learning dimensions of circumstantial and lifelong activists

This paper explores the informal and social learning dimensions of activists as they learn skills and knowledge through participating in social action. In doing this I draw on Lave and Wenger's epistemology of situated learning and Bourdieu's theory of "habitus". I argue activists learn an array of community development skills in the social environment of activism. I claim activists' learning is cognitive, embodied and situated in practice. This paper is based on empirical research in Australia, where in-depth interviews were conducted with activists to uncover their important pedagogy. It explores the learning dimensions of two groups of activists. "Lifelong activists" who have generally been involved in student politics and have participated in activism over many years, and "circumstantial activists" who become involved in protest due to a series of life circumstances. This paper claims that while both groups' learning is social and informal, lifelong activists tend to develop their skills incrementally by being involved in the fertile site of student politics. On the other hand, circumstantial activists, not having had the benefit of early immersion in a community of practice, are rapid learners. They are frequently taken out of their comfort zone as activists and need to acquire new knowledge and skills urgently in order to practise effectively. Some circumstantial activists remain on the periphery of activism and never fully immerse themselves in the practices of activism. I argue there is much to be gained from understanding learning in social action, an epistemology of adult learning which deserves greater prominence in current adult education discourse.

Digital oral feedback on written assignments as professional learning for teacher educators: a collaborative self-study

This article reports on a self-study of teacher educators involved in a preservice teacher unit on literacy. In this study the teacher educators provided the preservice teachers with digital oral feedback about their final unit of work. Rather than marking written work as individual lecturers, we collaboratively read each assignment and recorded a sound file of our conversation. We constructed our collaborative marking of each assignment as a “cultural gift” to our own professional learning. We found that we were providing more in-depth feedback on the assessment criteria for each assignment than we would have with written feedback prepared individually. We also uncovered tensions in relation to our preferred modalities associated with the digital marking.