The Practical Use of Problem Encoding Allowing Cheap Fitness Computation of Mutated Individuals
Journal Title: Annals of Computer Science and Information Systems - Year 2018, Vol 15, Issue
Abstract
The usual assumption in the Evolutionary Computation field is that a cost of computing single fitness function evaluation is at last similar for all cases. Such assumption does not have to be true. In this paper we consider the recently proposed Problem Encoding Allowing Cheap Fitness Computation of Mutated Individuals (PEACh) effect that allows to significantly reduce the computation load of some of the fitness computations that occur during the evolutionary method run. To the best of our knowledge, it is the first experimental analysis that investigates the results of PEACh application to methods solving NP-hard practical problems.
Authors and Affiliations
Michał Przewoźniczek, Marcin Komarnicki
Keywords
Related Articles
- EP ID EP569794
- DOI 10.15439/2018F331
- Views 24
- Downloads 0
Detection of Malicious Executables Using Rule Based Classification Algorithms
Machine Learning class rule has varied packages together with classification, clustering, will understand association rules furthermore and is capable of the method an enormous set of the information set as measure super...
Testing the Algorithm of Area Optimization by Binary Classification with Use of Three State 2D Cellular Automata in Layers
The paper is dedicated to a new algorithm of optimization in the sense of the area. Proposed method joins a few issues. First one is utilizing data from the set of sensors monitoring the area put into optimization. The s...
A Non-Deterministic Strategy for Searching Optimal Number of Trees Hyperparameter in Random Forest
In this paper, we present a non-deterministic strategy for searching for optimal number of trees hyperparameter in Random Forest (RF). Hyperparameter tuning in Machine Learning (ML) algorithms is essential. It optimizes...
Modular Multi-Objective Deep Reinforcement Learning with Decision Values
In this work we present a method for using Deep Q-Networks (DQNs) in multi-objective environments. Deep Q-Networks provide remarkable performance in single objective problems learning from high-level visual state represe...
Representation Matters: An Unexpected Property of Polynomial Rings and its Consequences for Formalizing Abstract Field Theory
In this paper we develop a Mizar formalization of Kronecker's construction, which states that for every field $F$ and irreducible polynomial $p \in F[X]$ there exists a field extension $E$ of $F$ such that $p$ has a root...