The recurrent buck-propagation ulgorithm for nearal nefwaorks has been implemerr~etl on the C’orlnecrion Machine. a massively purullel processor. Two fandamerr~ully different Lqq&~ architectlrrt~s underlying the nets Klere trsted: one bused on arcs. the other on node\. Confirming the predominunce of’ (,o1~11111(tIi(,(ltioll over compururion. peyformunce meusuremenls nnderscore Ihe necessi& lo m...

There are now several versions of Lisp for massively parallel SIMD architec-tures like the Thinking Machines Connection Machine. We describe here the extensions made to EuLisp for data-parallel programming and their implementation on a speciic platform, a MasPar MP-1. Plural EuLisp, in keeping with the rest of the language, presents a collection of simple orthogonal operators which capture the ...

we tried to increase semantic in the visual stock information system. Firstly, the semantic entity-relation model was given after studying the contents in visual stock information system and the hierarchical classification was shown. Then, semantic metadata and visual ontology was designed. For the implementation of VSIS, ontology reuse was considered which included ontology reuse model, the re...

CAPER is a case-based planning system that makes use of the massive parallelism of the Connection Machine to access a large memory of hundreds or more cases that are not pre-indexed. Preliminary empirical results of these retrieval methods indicate their viability and scalability. These results have motivated the retrieval-intensive design of the complete system, which includes proposed plan ad...

We implement parallel algorithms for solving the time dependent Sclu'/Sdinger equation on the CM-2 supercomputer. These methods are unconditionally s~able as well as unata~' at each time step and have the advantage of being spatially local and explicit. We show l~ow to ~dsualize the dynamics of quantum scattering using techniques for vlsuaIizing complex wave Iuncfions. Several. scattering probl...

A new technique for the efficient asynchronous discrete eventdriven simulation of parallel shared-memory computers is proposed. Our execution-driven methodology, while introducing minimal synchronization overhead to maintain a coherent distributed event causality relation, allows complete virtualization of the design at all levels and therefore is very flexible. We give a detailed description o...

This paper describes a parallel real-time stereomatching algorithm and its implementation on the Connection MachineTM computing system. computer, a new massively parallel The main features of the algorithm are 1) real-time performance, 2) the full exploitation of the OPdering constraint, 3) a representation that easily maps onto a parallel computer architecture, and 4) the ability to efficientl...