According to one brain-theoretical view, high~!:.brainful1ctionsarebased on processing_!!l1j.ts called cell as~~mbJiys. <::ell assemblies are large groups of corticalpyramidal neurons with strong and reclproc-al internal connections. C~lla,ssemblies develop in a randomIy-connected neuronal network when sets of neurons are frequently attive-simillfaneolisly so that their connectionsEstrengthen (...

tic knowledge to aid decision-making has been studied Planners have traditionally not handled domain uncertainty, postponing that poesib’xlity to error monitoring routines during the execution of the plan. In real-world domains with incomplete knowledge, this results in inevitable delays d’-e to rep]annlug. This paper describes a planner that considers the rellabflity of the agent’s actions (le...

Mercure is an information retrieval system based on a connexionist approach and modeled by a multi-layer network. The network is composed of a query layer (set of query terms), of a term layer (representing the indexing terms) and of a document layer [Bougha 99]. Mercure includes the implementation of retrieval process based on spreading activation forward and backward through the weighted link...

This paper proposes a method for measuring semantic similarity between words as a new tool for text analysis. The similarity is measured on a semantic network constructed systematically from a subset of the English dictionary, LDOCE (Longman Dictionary of Contemporary English). Spreading activation on the network can directly compute the similarity between any two words in the Longman De ning V...

Content analyses have consistently documented the disproportionate portrayal of Black Americans as criminals in the news. This experiment examines the impact of such portrayals on consumers by investigating the relationship between viewer ethnicity, viewing Black criminal suspects in the news, and beliefs related to public policy. Participants viewed a 30-minute local newscast containing crime ...

We present a novel approach that transforms the weighting task to a typical coarse-grained classification problem, aiming to assign appropriate weights for candidate expansion terms, which are selected from WordNet and ConceptNet by performing spreading activation. This transformation benefits us to automatically combine various features. The experimental results show that our approach successf...

An e cient retrieval of a relatively small number of relevant cases from a huge case base is a crucial subtask of Case-Based Reasoning (CBR). In this report, the framework of Case Retrieval Nets is presented. The main idea of these nets is to construct a memory structure representing both, the contents of the case base, and the knowledge about similarity in the domain considered. Then, a spread...

Massively Parallel Artificial Intelligence is a new and growing area of AI research, enabled by the emergence of massively parallel machines. It is a new paradigm in AI research. A high degree of par­ allelism not only affects computing performance, but also triggers drastic change in the approach to­ ward building intelligent systems; memory-based reasoning and parallel marker-passing are exam...

2 Mercure model Mercure is an information retrieval system based on a connexionist approach and modeled by a multi-layered network. The network is composed of a query layer (set of query terms), a term layer (representing the indexing terms) and a document layer [Boughanem99]. Mercure includes the implementation of a retrieval process based on spreading activation forward and backward through t...

Graph ranking algorithms such as PageRank and HITS share the common idea of calculating eigenvectors of graph adjacency matrices. This paper shows that the power method usually used to calculate eigenvectors is also present in a spreading activation search. In addition, we empirically show that spreading activation algorithm is able to converge on periodic graphs, where power method fails. Furt...