Multiprocessor Document Allocation: a Neural Network Approach
Abdulaziz Al-Sehibani, Kishan G. Mehrotra, Chilukuri Krishna Mohan, Sanjay Ranka · Syracuse University Libraries (Syracuse University) · 1994
We consider the problem of distributing the documents to a given set of processors so that the load on each processor is as equal as possible and the amount of communication is as small as possible. This is an NP-Complete problem. We apply continuous as well as discrete Hopfield neural networks to obtain suboptimal solutions for the problem. These networks perform better than a genetic algorithm for this task proposed by Frieder et al. [4]; in particular, the continuous Hopfield network performs extremely well. Keywords: Document Allocation, Hopfield Network, Multiprocessor, Information Retrieval 1 Introduction Multiprocessor systems with distributed memory are powerful tools for information retrieval. These systems can support multiple queries simultaneously, with various documents distributed among the processors. Efficient exploitation of parallelism in such systems requires fast access to documents. In this paper, we address the task of allocating documents onto processors to a...