Global optimization, searching and machine learning method based on Lamarck's principle of inheritance of acquired characters

Abstract

The invention discloses a global optimization, searching and machine learning method based on a Lamarck's principle of inheritance of acquired characters. The global optimization, searching and machine learning method comprises the steps of: step 1, constructing an objective function f(x) according to a problem object; step 2, encoding the problem object into a chromosome of a genetic algorithm, automatically calculating or inputting operation parameters, and performing initialization; step 3, performing iterative optimization on a current (kth generation) population Gk={Pk<1>, Pk<2>,..., Pk<S>} by adopting a Lamarck's ''operator of inheritance of acquired characters'' and a ''use and disuse operator'' according to evaluation of the objective function f(x); step 4, and outputting an optimal solution set of the problem object. The global optimization, searching and machine learning method integrates the ''inheritance of acquired characters'' and ''use and disuse'' natural laws of Lamarck's evolution theory with the modern ''epigenetics'' and the ''survival of the fittest'' natural law of Darwin's evolution theory, simplifies the structure of the genetic algorithm, overcomes the multiple technical defects of the existing algorithm, and improves the efficiency, global optimality and sustainability of late evolution of the algorithm, so that more global optimization, searching and machine learning problems can be better solved.

Description

technical field [0001] The invention relates to the technical field of computer programs, including artificial intelligence, and in particular to a global optimization, search and machine learning method based on genetic algorithms. Background technique [0002] In order to solve technical problems such as global optimization, search and machine learning, ordinary genetic algorithms use Darwin's "survival of the fittest" natural evolution law, and repeatedly apply three operators: selection operator, crossover operator and mutation operator , the search speed of the algorithm is relatively slow, and the search accuracy is relatively low; moreover, the local search ability of the genetic algorithm is poor, which leads to the low search efficiency of the algorithm in the later stage of evolution; in practical applications, the genetic algorithm is prone to premature convergence, what kind of The selection method must not only preserve the excellent individuals, but also mainta...

AI Technical Summary

Problems solved by technology

Secondly, according to Lamarck's use-for-use, waste-retreat natural law, a "use-for-use, waste-retreat operator" is invented, which can be used to replace the innate mutation operator in the ordinary genetic algorithm, so that the acquired directional mutation operation can be performed in the same generation, so that The mutation operation produces new technical effects, improves the performance of the genetic algorithm, and makes it solve more and better problems such as global optimization, search and machine learning

Images