scholarly journals Adaptive Learning of Process Control and Profit Optimization Using a Classifier System

1995 ◽  
Vol 3 (2) ◽  
pp. 177-198 ◽  
Author(s):  
A. H. Gilbert ◽  
Frances Bell ◽  
Christine L. Valenzuela
Keyword(s):  
Genetic Algorithm ◽  
Process Control ◽  
Chemical Reaction ◽  
Adaptive Learning ◽  
Profit Sharing ◽  
Reaction Parameters ◽  
Market Conditions ◽  
Classifier System ◽  
Profit Optimization ◽  
Apportionment Of Credit

A classifier system is used to learn control and profit optimization of a batch chemical reaction. Ability to learn different market conditions and changes to reaction parameters is demonstrated. The profit sharing algorithm is used for apportionment of credit. The greater effectiveness of the use of the genetic algorithm over apportionment of credit alone or the random replacement of low strength rules is also shown. The classifier system is unusual in having more than one action per rule.

SELF-ADAPTIVE LEARNING CLASSIFIER SYSTEM

2010 ◽  
Vol 19 (01) ◽  
pp. 275-296 ◽  
Author(s):  
OLGIERD UNOLD
Keyword(s):  
Mutation Rate ◽  
Adaptive Learning ◽  
Adaptive Mutation ◽  
Learning Classifier System ◽  
Classifier System ◽  
Learning Classifier ◽  
Adaptive Parameters ◽  
Proposed Model ◽  
Fixed Parameter ◽  
Self Adaptive

This article introduces a new kind of self-adaptation in discovery mechanism of learning classifier system XCS. Unlike the previous approaches, which incorporate self-adaptive parameters in the representation of an individual, proposed model evolves competitive population of the reduced XCSs, which are able to adapt both classifiers and genetic parameters. The experimental comparisons of self-adaptive mutation rate XCS and standard XCS interacting with 11-bit, 20-bit, and 37-bit multiplexer environment were provided. It has been shown that adapting the mutation rate can give an equivalent or better performance to known good fixed parameter settings, especially for computationally complex tasks. Moreover, the self-adaptive XCS is able to solve the problem of inappropriate for a standard XCS parameters.

Fabrication of Semiconductor Nano-particles in the Protein Cage of Apoferritin

2005 ◽  
Vol 873 ◽  
Author(s):  
Kenji Iwahori ◽  
Keiko Yoshizawa ◽  
Masahiro Muraoka ◽  
Ichiro Yamashita
Keyword(s):  
Chemical Reaction ◽  
Reaction System ◽  
Nano Particles ◽  
Internal Cavity ◽  
Reaction Parameters ◽  
Synthesis System ◽  
X Ray ◽  
Protein Cage ◽  
High Resolution Tem ◽  
Chemical Reaction System

AbstractWe specially designed a slow chemical reaction system to synthesize the zinc selenide nanoparticles (ZnSe NPs), in the cavity of the cage-shaped protein, apoferritin. The newly designed chemical synthesis system for ZnSe NPs makes the chemical reaction of compound semiconductor element ions dramatically slow, resulting in that ZnSe NPs can be synthesized in the internal cavity of the apoferritin. The ZnSe NPs synthesized by the optimized reaction parameters are efficiently produced in the aqueous solution. The UVVis spectrum analysis of synthesized ZnSe-ferritin suggests that the formation of ZnSe nuclei in the apoferritin cavity takes about 6 hours by using our slow chemical reaction system. The synthesized ZnSe NPs were characterized by high resolution TEM, X-ray powder diffraction (XRD) and Energy Dispersive Spectrometory (EDS) and it was revealed that the synthesized NPs are a collection of cubic ZnSe crystals.

scholarly journals ZCS: A Zeroth Level Classifier System

1994 ◽  
Vol 2 (1) ◽  
pp. 1-18 ◽  
Author(s):  
Stewart W. Wilson
Keyword(s):  
Genetic Algorithm ◽  
Action Selection ◽  
Q Learning ◽  
Classifier System ◽  
General Classifier ◽  
And Performance ◽  
Temporary Memory

A basic classifier system, ZCS, is presented that keeps much of Holland's original framework but simplifies it to increase understandability and performance. ZCS's relation to Q-learning is brought out, and their performances compared in environments of two difficulty levels. Extensions to ZCS are proposed for temporary memory, better action selection, more efficient use of the genetic algorithm, and more general classifier representation.

scholarly journals Classifier Fitness Based on Accuracy

1995 ◽  
Vol 3 (2) ◽  
pp. 149-175 ◽  
Author(s):  
Stewart W. Wilson
Keyword(s):  
Genetic Algorithm ◽  
Reinforcement Learning ◽  
Strength Parameter ◽  
System Research ◽  
Classifier Systems ◽  
Expected Payoff ◽  
Classifier System ◽  
Wide Range ◽  
Accuracy Criterion

In many classifier systems, the classifier strength parameter serves as a predictor of future payoff and as the classifier's fitness for the genetic algorithm. We investigate a classifier system, XCS, in which each classifier maintains a prediction of expected payoff, but the classifier's fitness is given by a measure of the prediction's accuracy. The system executes the genetic algorithm in niches defined by the match sets, instead of panmictically. These aspects of XCS result in its population tending to form a complete and accurate mapping X × A → P from inputs and actions to payoff predictions. Further, XCS tends to evolve classifiers that are maximally general, subject to an accuracy criterion. Besides introducing a new direction for classifier system research, these properties of XCS make it suitable for a wide range of reinforcement learning situations where generalization over states is desirable.

Sign in / Sign up

Export Citation Format

Share Document