Abstract. This paper introduces the Assistive Kitchen as a comprehensive demonstration and challenge scenario for technical cognitive systems. We describe its hardware and software infrastructure. Within the Assistive Kitchen application, we select particular domain activities as research subjects and identify the cognitive capabilities needed for perceiving, interpreting, analyzing, and executing these activities as research foci. We conclude by outlining open research issues that need to be solved to realize the scenarios successfully. I.

Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that computer systems be imbued with the ability to configure themselves, diagnose failures, and ultimately repair themselves in response to these failures. However, despite convincing arguments that such a shift would be desirable, as of yet there has been little concrete progress made towards this goal. We view these problems as fundamentally machine learning challenges. Hence, this article presents a new network simulator designed to study the application of machine learning methods from a system-wide perspective. We also introduce learning-based methods for addressing the problems of job routing and CPU scheduling in the networks we simulate. Our experimental results verify that methods using machine learning outperform reasonable heuristic and hand-coded approaches on example networks designed to capture many of the complexities that exist in real systems.

Abstract not found

this paper, I chart the successes and mindset used by database researchers to generate efficient query processing programs automatically. I argue that the road that they have so successfully followed is the same road that the generative programming, domain-specific languages, and automatic programming communities are now traversing

Abstract. The newly established cluster of excellence COTESYS 1 investigates the realization of cognitive capabilities such as perception, learning, reasoning, planning, and execution for technical systems including humanoid robots, flexible manufacturing systems, and autonomous vehicles. In this paper we describe cognitive technical systems using a sensor-equipped kitchen with a robotic assistant as an example. We will particularly consider the role of Artificial Intelligence in the research enterprise. Key research foci of Artificial Intelligence research in COTESYS include (◦) symbolic representations grounded in perception and action, (◦) first-order probabilistic representations of actions, objects, and situations, (◦) reasoning about objects and situations in the context of everyday manipulation tasks, and (◦) the representation and revision of robot plans for everyday activity. 1

Computer systems are rapidly becoming so complex that maintaining them with human support stas will be prohibitively expensive and inecient. In response, visionaries have begun proposing that computer systems be imbued with the ability to con gure themselves, diagnose failures, and ultimately repair themselves in response to these failures. However, despite convincing arguments that such a shift would be desirable, as of yet there has been little concrete progress made towards this goal. We view these problems as fundamentally machine learning challenges. Hence, this article presents a new network simulator designed to study the application of machine learning methods from a system-wide perspective. We also introduce learning-based methods for addressing the problems of job routing and CPU scheduling in the networks we simulate. Our experimental results verify that methods using machine learning outperform reasonable heuristic and hand-coded approaches on example networks designed to capture many of the complexities that exist in real systems.

Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that computer systems be imbued with the ability to configure themselves, diagnose failures, and ultimately repair themselves in response to these failures. However, despite convincing arguments that such a shift would be desirable, as of yet there has been little concrete progress made towards this goal. We view these problems as fundamentally machine learning challenges. Hence, this article presents a new network simulator designed to study the application of machine learning methods from a system-wide perspective.

Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that computer systems be imbued with the ability to configure themselves, diagnose failures, and ultimately repair themselves in response to these failures. However, despite convincing arguments that such a shift would be desirable, as of yet there has been little concrete progress made towards this goal. We view these problems as fundamentally machine learning challenges. Hence, this article presents a new network simulator designed to study the application of machine learning methods from a system-wide perspective. We also introduce learning-based methods for addressing the problems of packet routing and CPU scheduling in the networks we simulate. Our experimental results verify that methods using machine learning outperform heuristic and hand-coded approaches on an example network designed to capture many of the complexities that exist in real systems.

Abstract. Early visions of case-based reasoning stressed its broad applicability. Realizing the dream of near-universal application of CBR will require lowering the boundaries to entry for CBR applications. This position paper proposes, as a step toward that goal, the challenge problem of developing CBR systems with more human-like capabilities to exploit large multi-use memories to assemble “latent cases, ” e.g., building missing cases from fragments drawn from existing external information sources such as the the Web. This approach is inspired by the Dynamic Memory [1] model of human memory. The paper identifies key research areas for harnessing latent cases, including: (1) structural indexing, (2) case assembly, evaluation, and repair, (3) introspective reasoning, (4) provenance capture and analysis, and (5) storage/recall methods for dynamic cases.

Abstract. We discuss metacognitive modelling as enhancement to cognitive modelling and computing. Metacognitive control mechanisms should enable AI systems to self-reflect, reason about their actions, and to adapt to new situations. In this respect, we propose implementation details of a knowledge taxonomy and an augmented data mining life cycle.