With the increasing availability of parallel machines and the raising of interest in large scale and real world applications, research on parallel processing for Artificial Intelligence (AI) is gaining greater importance in the computer science environment. Many applications have been implemented and delivered but the field is still considered to be in its infancy.This book assembles diverse aspects of research in the area, providing an overview of the current state of technology. It also aims to promote further growth across the discipline. Contributions have been grouped according to their subject: architectures (3 papers), languages (4 papers), general algorithms (6 papers), and applications (5 papers). The internationally sourced papers range from purely theoretical work, simulation studies, algorithm and architecture proposals, to implemented systems and their experimental evaluation.Since the book is a second volume in the parallel processing for AI series, it provides a continued documentation of the research and advances made in the field. The editors hope that it will inspire readers to investigate the possiblities for enhancing AI systems by parallel processing and to make new discoveries of their own!
Table of Contents:
Architectures. Hybrid systems on a multi-grain parallel architecture (G. Ouvradou, A.P. Maubant, A. Thépaut). An abstract machine for implementing connectionist and hybrid systems on multi-processor architectures (Y. Lallement, T. Cornu, S. Vialle). A dense, massively parallel architecture (T. Reski, W.B. Strothmann). Languages. Using confluence to control parallel production systems (J.G. Schmolze, W. Snyder). Toward an architecture independent high level parallel programming model for artificial intelligence (M.S. Berlin). An object-oriented approach for programming the connection machine (L. Hotz). Automatic parallelisation of LISP programs (E. Furse, K.H. Sewell). General Algorithms. Simulation analysis of static partitioning with slackness (C.B. Suttner, M.R. Jobmann). Parallel distributed realization for constraint satisfaction (W. Hower, S. Jacobi). A first step towards the massively parallel game-tree search: a SIMD approach (V.-D. Cung, L. Gotte). Initialization of parallel branch-and-bound algorithms (D. Henrich). A model for parallel deduction (U. Assmann). Applications. Toward real-time motion planning (D.J. Challou, M. Gini, V. Kumar). Toward massively parallel spoken language translation (K. Oi, E. Sumita, O. Furuse, H. Iida, H. Kitano). Weather forecasting using memory-based reasoning (T. Mohri, M. Nakamura, H. Tanaka). Scalability of an OR-parallel theorem prover on a network of transputer - a modelling approach (J. Schumann, M. Jobmann). A coarse grained parallel induction heuristic (R.A. Pearson). Fuzzy logic controlled dynamic allocation system (K. Stoffel, I. Law, B. Hirsbrunner).
