In this talk I will briefly outline and survey some developments in the field of statistical relation learning, especially focussing on logical approaches. Statistical relational learning is a novel research stream within artificial intelligence that combines principles of relational logic, learning and probabilistic models. This endeavor is similar in spirit to the developments in Neural Symbo...

This paper examines the implications of connectionist models of cognition for second language theory. Connectionism offers a challenge to the symbolic models which dominate cognitive science. In connectionist models all knowledge is embodied in a network of simple processing units joined by connections which are strengthened or weakened in response to regularities in input patterns. These model...

Today, building automation is advancing from simple monitoring and control tasks of lightning and heating towards more and more complex applications that require a dynamic perception and interpretation of different scenes occurring in a building. Current approaches cannot handle these newly upcoming demands. In this article, a bionically inspired approach for multimodal, dynamic scene perceptio...

Symbolic interactionist principles of sociology are based on the idea that human action is guided by culturally shared symbolic representations of identities, behaviours, situations and emotions. Shared linguistic, paralinguistic, or kinesic elements allow humans to coordinate action by enacting identities in social situations. Structures of identitybased interactions can lead to the enactment ...

Determination of terrain data features in a high resolution terrain data model are required in a large variety of applications where visualization is an important aspect. This is a complex problem because a terrain model is generally a mapping of the reality into a continuous 3D surface model of arbitrary shape, requiring an extremely large amount of data especially when a high resolution is re...

Domains and Solvers for Sets Reasoning Arlen Cox, Bor-Yuh Evan Chang, Huisong Li, Xavier Rival University of Colorado Boulder Inria/CNRS/ENS Paris/PSL* Abstract. When constructing complex program analyses, it is often useWhen constructing complex program analyses, it is often useful to reason about not just individual values, but collections of values. Symbolic set abstractions provide building...

Pattern matching and variable binding are easily implemented in conventional computer architectures, but not necessarily in all architectures. In a distributed neural network architecture each symbol is represented by activity in many units and each unit contributes to the representation of many symbols. Manipulating symbols using this type of distributed representation is not as easy as with a...

Inspired by recent work in the theory of central projections onto hypersurfaces, we characterize self-linked perfect ideals of grade 2 as those with a Hilbert–Burch matrix that has a maximal symmetric subblock. We also prove that every Gorenstein perfect algebra of grade 1 can be presented, as a module, by a symmetric matrix. Both results are derived from the same elementary lemma about symmetr...

Addressing integrative possibilities between psychology and anthropology, this paper aims to design conceptual linkages between semiotic-cultural constructivist psychology and the anthropological theory of Amerindian perspectivism. From the psychological view, it is the interdependence between the structural and processual dimensions of the personal culture that makes parallels with Amerindian ...