On the range of applicability of an artificial intelligence machine

摘要

Considerable interest has recently been expressed in the construction of parallel machines capable of significant performance and cost/performance improvements in various artificial intelligence applications. In this paper, we consider the capabilities of a particular massively parallel machine called NON-VON, an initial prototype of which is currently operational at Columbia University, for the efficient execution of a rather wide range of AI tasks. The paper provides a brief overview of the general NON-VON architecture, and summarizes certain performance projections, derived through detailed analysis and simulation, in the areas of rule-based inferencing, computer vision, and knowledge-base management.In particular, summaries are presented of projections derived for the execution of OPS5 production systems, the performance of a number of low- and intermediate-level image understanding tasks, and the execution of certain “difficult” relational algebraic operations having relevance to the manipulation of knowledge bases. The results summarized in this paper, most of which are based on benchmarks proposed by other researchers, suggest that NON-VON could provide a performance improvement of as much as several orders of magnitude on such tasks by comparison with a conventional sequential machine of comparable hardware cost.