for the presence of parts and their spa-tial relationships within image patches. Hence our model combines the represen-tational flexibility of graphical models with the efficiency and statistical power of DCNNs. Our method significantly outperforms the state of the art methods on the LSP and FLIC datasets and also

-cessing is integrated with analogical mapping, leading to the flexible build-up of represen-tations appropriate to a given context.

This paper describes a method for learning flexible concepts. by which are meant concepts that lack precise definition and are contextqlependent. To describe such concepts, the method employs a two-tiered represen- tation. in which the first tier captures explicitly basic concept properties

to depend on exogenous states, interpreted as information. My axioms yield a represen-tation that uniquely identi…es beliefs, provided information is su ¢ ciently relevant for choice. The result is suggested as a choice theoretic foundation for the assumption, commonly made in the (incomplete) contracting

that RITL is implemented via brain circuits centered on lateral prefrontal cortex. We then build on this and the recent discovery of compositional represen-tations within lateral prefrontal cortex to develop an integra-tive theory of cognitive flexibility and cognitive control that identifies mechanisms

, providing a signature of top-downbias over perception. Furthermore, demands on cognitive control arising from the task structuremodulated context represen-tation, which was found to be strongest after a shift in task rules. When context representation in frontoparietal areas increased in strength

to heterogeneous data sources, they can-not properly integrate the diversity of stored representa-tions. The objective of the European project described in this paper, MurMur1, is to enhance GIS (or DBMS) functionality so that, relying on more flexible represen-tation schemes, users may easily manage information

representation of a three-dimensional arrangement. We also inspirit the framework in two steps. First, we show that the well-known family of algebraic surfaces fulfils the frame-work’s requirements. As robust implementations on these surfaces are lacking these days, we consider the framework to be an impor

There is an increasingly pressing need to develop document analysis methods that are able to cope with images of documents containing printed regions of complex shapes. Contrary to the bounding-box represen-tation used in most past page segmentation and classifi-cation approaches which assume

scene can allow successful topographical per-ception without it, possibly via a less flexible parahippocampal represen-tation. VC 2006 Wiley-Liss, Inc. KEY WORDS: amnesia; short-term memory; long-term memory; perception; spatial; allocentric; cognitive map; aging