Scatter programming

Abstract

The core of artificial intelligence and machine learning is to get computers to solve problems automatically.One of the great tools that attempt to achieve that goal is Genetic Programming (GP). As alternatives to GP, Scatter Programming (SP) is proposed in this paper. One of the main features of SP is to exploit local search in order to overcome some recently addressed drawbacks of GP, especially its highly disruption of its main operations; crossover and mutation. This work shows that SP has promising performance and results in solving machine learning problems.

Automatic Heuristic Generation with Scatter Programming to Solve the Hybrid Flow Shop Problem

“…The three metaheuristic programming approaches are GP, SP with shaking [7] (SP-S), and the proposed SP with one-point traversal shaking (SP-OPTS). The five existing dispatching rules are as follows:…”

“…Pruning search does not add any branches to the tree but cuts some branches from the tree and replaces them with leaf nodes generated randomly. The experimental results in [7] show that SP is stable and effective in solving machine learning problems. However, the disruption of the three local improvement methods is also high.…”

“…All solutions in Sub-Set are improved by the local improvement method. An intensification search procedure called shaking search was developed in [7]. In shaking search, n nodes in the tree are selected randomly and updated by different random alternatives.…”

“…Finally, Ref-Set is updated by the improved solutions. In 2010, Hedar and Osman [7] proposed SP to solve machine learning problems with three tree-based local search methods, namely, shaking search, grafting search, and pruning search. Shaking search selects some nodes of the tree and replaces them with random ones.…”

“…An automatic heuristic generation method with scatter programming [7] (SP) is developed in this paper for the HFS problem. The main operators of SP, such as children generation and local improvement methods, are utilized to balance intensification and diversification.…”