Related Concept Videos
Genetic Screens
Forward genetic screens
Forward or “classical” genetic screens involve creating random mutations in an organism’s DNA using radiation, mutagens, or insertion of additional bases, which result in visible changes...
Combinatorial Gene Control
The expression of more than 30,000 genes is controlled by approximately 2000-3000 transcription factors. This is possible because a single transcription factor can recognize more than one regulatory sequence. The specificity in gene...
X-Inactivation
Methods of Nuclear Reprogramming
The Ratio of X Chromosome to Autosomes
Normal male Drosophila has a ratio of one X chromosome to two sets of autosomes. In contrast, normal female Drosophila...
Genetic Variation
Genes exist in different versions called alleles, which...
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
A Systematic Review of Machine-Learning Solutions in Anaerobic Digestion.
On the Emergence of Intersexual Selection: Arbitrary Trait Preference Improves Female-Male Coevolution.
Computing Optimal Populations for Binary Problems using Logic Minimization.
Enhancing Generalization and Scalability for Multi-Objective Optimization with Population Pre-Training.
XCS for Sequential Perceptual Aliasing in Multi-Step Decision Making.
A dynamic multi-objective evolutionary algorithm using dual-space prediction and surrogate-based sampling.
Adapting MOEA/D to CMA-ES for Dealing with Ill-conditioned Multiobjective Problems.
Editorial of the Special Issue: Parallel Problem Solving from Nature PPSN 2024 Extended Versions of Best Paper Candidates.
Related Experiment Video
Updated: May 22, 2026

Inherent Dynamics Visualizer, an Interactive Application for Evaluating and Visualizing Outputs from a Gene Regulatory Network Inference Pipeline
Published on: December 7, 2021
Dynamical genetic programming in XCSF.
1Department of Computer Science and Creative Technologies, University of the West of England, Bristol, BS16 1QY, United Kingdom richard.preen@live.uwe.ac.uk
This study introduces dynamic arithmetic networks for the XCSF learning classifier system, achieving competitive performance in reinforcement learning and symbolic regression tasks. The approach also shows promise for financial time series prediction.
Area of Science:
- Machine Learning
- Artificial Intelligence
- Computational Neuroscience
Background:
- Learning classifier systems (LCS) traditionally use binary encodings or neural networks.
- Existing LCS methods face challenges in handling continuous-valued reinforcement learning and symbolic regression.
Purpose of the Study:
- To investigate the efficacy of a temporally dynamic symbolic representation within the XCSF learning classifier system.
- To evaluate the performance of dynamical arithmetic networks for continuous-valued reinforcement learning and symbolic regression.
- To explore the application of this novel representation for financial time series prediction.
Main Methods:
- Utilized dynamical arithmetic networks to represent condition-action rules in the XCSF system.
- Applied the system to solve continuous-valued reinforcement learning problems.
- Employed the system for symbolic regression on composite polynomial tasks.
- Sampled network outputs at varying temporal intervals for financial time series prediction.
Main Results:
- Achieved competitive performance compared to traditional genetic programming on polynomial tasks.
- Demonstrated the system's capability in continuous-valued reinforcement learning.
- Successfully performed multistep-ahead predictions on a financial time series.
Conclusions:
- Temporally dynamic symbolic representations, specifically dynamical arithmetic networks, offer a viable alternative for LCS.
- The proposed method shows strong potential for both complex learning tasks and time series forecasting.

