We consider the fundamental complexity of intelligent systems, and argue that some form of learning is essential in order to acquire the amount of information necessary to specify such a system. In this view, learning is essentially a means of acquiring large amounts of structured information by relatively simple recoding of information owing down high-bandwidth channels (the senses) from a pre...

Within the school environment, interactions between people and interactions between people and things are affected by situated, contextual factors. Context includes not only physical characteristics, but psychological, and social characteristics as well. Moreover, context is understood in terms of both past and present circumstances. Computer applications designed to support group activity, lik...

Extractive summarization suffers from irrelevance, redundancy and incoherence. Existing work shows that abstractive rewriting for extractive summaries can improve the conciseness readability. These systems consider extracted as only input, which is relatively focused but lose important background knowledge. In this paper, we investigate contextualized rewriting, ingests entire original document...

Ontologies strive to offer a interconnected, hierarchical systems of categories to guide our actions in a complex world. But the boundaries of these categories are highly context-dependent, and what constitutes a prototypical category member in one context may be atypical or unrepresentative in another. In this paper we outline a dynamic, trainable, bottom-up view of category structure based on...

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . x 1 Problem Statement . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 1.1 The Difficulty of Human-Robot Interaction . . . . . . . . . . . . . . . . . . . 1 1.2 “Robotic Motion” . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 1.2.1 Prior Work . . . . . . . . . . . . . . . . ....

Central to the semantic web are ontologies: shared conceptualizations of domains of interest expressed in an ontology language such as OWL. Rule languages complement ontology languages. For large heterogeneous bodies of knowledge on the semantic web, contextualized knowledge repositories facilitate the organization of ontological concepts. In this paper we propose a similar mechanism – contextu...

Currently, task-specific support information in aircraft maintenance is mostly provided using paper-based solutions, which are burdensome, slow and prone to error. Next to these issues, Aircraft Maintenance Technicians (AMTs) have very limited on-site access to support information. This leads to 15-30% of handson-aircraft time being wasted on acquiring the right information or not using mainten...

The notion of context appears in several disciplines, including computer science, in various forms. In this paper, we are concerned with a notion of context in the area of information bases. First, we present a general definition whereby a context is seen as a set of objects, within which each object has a set of names and possibly a reference: the reference of the object is another context whi...

The paper is devoted to two problems: (1) reinforcement of SVM algorithms, and (2) justification memorization mechanisms for generalization. Current algorithm was designed the case when risk set nonnegative slack variables defined by l1 norm. In this paper, along with that classical norm, we consider risks l2 norm l∞ Using these norms, formulate several modifications existing show resulting mod...