Binary Decision Diagrams (BDDs) have proved to be a powerful representation for Boolean functions. Particularly, they are a very useful data structure for the symbolic model checking of digital circuits and other finite state systems, as well as other problems. Nevertheless, the size of the BDD representation of these functions is highly dependent on the order of the function arguments, also called variables, and to nd such good ordering is an NP-Complete problem. Many heuristics have been proposed to solve this problem, as the depth-first traversal algorithm, one of the best known techniques, and the genetic algorithm found in [6]. In this paper, we present a improvement to them, through a parallel genetic algorithm, and compare its experimental results with those obtained from an interleaving-based implementation of the depth-first traversal algorithm, applying them to the ISCAS85 benchmark circuits.

Binary Decision Diagrams (BDDs) have proved to be a powerful representation for Boolean functions.

Binary Decision Diagrams (BDDs) have proved to be a powerful representation for Boolean functions. Particularly, they are a very useful data structure for the symbolic model checking of digital circuits and other finite state systems, as well as other problems. Nevertheless, the size of the BDD representation of these functions is highly dependent on the order of the function arguments, also called variables, and to find such good ordering is an NP-Complete problem. Many heuristics have been proposed to solve this problem, as our Parallel Genetic Algorithm presented in [4], where we got excellent results in terms of parallelization. Now, we present a new version of our algorithm, this time with a cache system, together with experimental results.

A GRASP (Greedy Randomized Adaptive Search Procedure) is a metaheuristic for producing good-quality solutions of combinatorial optimization problems. It is usually implemented with a construction procedure based on a greedy randomized algorithm followed by local search. In this Chapter, we survey parallel implementations of GRASP. We describe simple strategies to implement independent parallel GRASP heuristics and more complex cooperative schemes using a pool of elite solutions to intensify the search process. Some applications of independent and cooperative parallelizations are presented in detail.

A Greedy Randomized Adaptive Search Procedure (GRASP) is a metaheuristic for combinatorial optimization. It usually consists of a construction procedure based on a greedy randomized algorithm and a local search. Path-relinking is an intensification strategy that explores trajectories that connect high quality solutions. We analyze two parallel strategies for GRASP with path-relinking and propose a criterion to predict parallel speedup based on experiments with a sequential implementation of the algorithm. Independent and cooperative parallel strategies are described and implemented for the 3-index assignment problem and the job-shop scheduling problem. The computational results for independent parallel strategies are shown to qualitatively behave as predicted by the criterion.

Stochastic Diffusion Search (sds) was introduced by Bishop (1989a) as an algorithm to solve pattern matching problems. It relies on many concurrent partial evaluations of candidate solutions by a population of agents and communication between those agents to locate the optimal match to a target pattern in a search space. In subsequent research, several variations on the original algorithmic formulation were proposed. It also became evident that its main principles – partial evaluation and communication between agents – can be employed to problems outside the pattern matching domain. The primary aim of this dissertation is to develop these expansive views further: sds is proposed as a metaheuristic, a generic heuristic procedure for solving problems through search. Furthermore, it is proposed as a challenge to the dominant metaphor in computer science: sequential computation. The thesis proceeds in a structured way by first considering all questions that can be asked about a heuristic procedure like sds: questions of a foundational nature, questions pertaining to mathematical analysis, questions about application domains and questions about physical implementation. It is to the foundational issues that most attention is devoted. Analogies with selective processes in natural and social systems are investigated, as well as analogies with other metaheuristic techniques from artificial intelligence. An attempt is made to categorise potential variants, and to establish what kind of problems sds would be the optimal problem-solving method for. The work aims to provide an expanded but structured understanding of sds, to give guidelines for future work, and to establish how progress in other scientific disciplines can be of use in the study of sds, and vice versa. Preface All sciences characterise the essential nature of the systems they study. These characterisations are invariably qualitative in nature, for they set the terms with which more detailed knowledge can be developed. A. Newell and H. Simon (Newell and Simon, 1976) Cybernetics is the science of defensible metaphors.

Abstract. We present a version of the CCP paradigm, which is both distributed and probabilistic. We consider networks with a fixed number of nodes, each of them possessing a local and independent constraint store. While locally the computations evolve asynchronously, following the usual rules of (probabilistic) CCP, the communications among different nodes are synchronous. There are channels, and through them different objects can be exchanged: constraints, agents and channel themselves. In addition, all this activities are embedded in a probabilistic scheme based on a discrete model of time, both locally and globally. Finally we enhance the language with the capability of performing an automatic remote synchronization of variables belonging to different constraint stores. 1

A protein is identified by a finite sequence of amino acids, each of them chosen from a set of 20 elements. The Protein Structure Prediction Problem, fundamental for biological and pharmaceutical research, is the problem of predicting the 3D native conformation of a protein, when its sequence of amino acids is known. All current mathematical models of the problem are affected by intrinsic computational limits, and by a disagreement on which is the most reliable energy function to be used.

Constraint-based approaches to stochastic dynamics of biological systems Candidate: