A WSI architecture for AI semantic networks

Many artificial intelligence (AI) applications need high performance computers that allow them to execute algorithms at reasonable speed. In recent years, researchers at universities and industry have developed new architectures in order to accomplish the performance required. A number of the AI algorithms require knowledge representation and manipulation which can be obtained by means of semantic networks. A WSI architecture dedicated to semantic network processing may have an impact on the AI field; since the parallelism in this application can be exploited by means WSI technology which offers a potential of higher reliability and speed. However, it is necessary to deal with some of the WSI problems, mainly defects on the silicon.<
>