Evolving Neural Networks through a Reverse Encoding Tree

Type
Conference Paper

Authors
Zhang, Haoling
Yang, Chao-Han Huck
Zenil, Hector
Kiani, Narsis A.
Shen, Yue
Tegner, Jesper

KAUST Department
Biological and Environmental Sciences and Engineering (BESE) Division
Bioscience Program

Preprint Posting Date
2020-02-03

Online Publication Date
2020-09-03

Print Publication Date
2020-07

Date
2020-09-03

Abstract
NeuroEvolution is one of the most competitive evolutionary learning strategies for designing novel neural networks for use in specific tasks, such as logic circuit design and digital gaming. However, the application of benchmark methods such as the NeuroEvolution of Augmenting Topologies (NEAT) remains a challenge, in terms of their computational cost and search time inefficiency. This paper advances a method which incorporates a type of topological edge coding, named Reverse Encoding Tree (RET), for evolving scalable neural networks efficiently. Using RET, two types of approaches – NEAT with Binary search encoding (Bi-NEAT) and NEAT with Golden-Section search encoding (GS-NEAT) – have been designed to solve problems in benchmark continuous learning environments such as logic gates, Cartpole, and Lunar Lander, and tested against classical NEAT and FS-NEAT as baselines. Additionally, we conduct a robustness test to evaluate the resilience of the proposed NEAT approaches. The results show that the two proposed approaches deliver improved performance, characterized by (1) a higher accumulated reward within a finite number of time steps; (2) using fewer episodes to solve problems in targeted environments, and (3) maintaining adaptive robustness under noisy perturbations, which outperform the baselines in all tested cases. Our analysis also demonstrates that RET expends potential future research directions in dynamic environments. Code is available from https://github.com/HaolingZHANG/ReverseEncodingTree.

Citation
Zhang, H., Yang, C.-H. H., Zenil, H., Kiani, N. A., Shen, Y., & Tegner, J. N. (2020). Evolving Neural Networks through a Reverse Encoding Tree. 2020 IEEE Congress on Evolutionary Computation (CEC). doi:10.1109/cec48606.2020.9185648

Acknowledgements
This work was initiated by Living Systems Laboratory at King Abdullah University of Science and Technology (KAUST) lead by Prof. Jesper Tegner and supported by funds from KAUST. Chao-Han Huck Yang was supported by the Visiting Student Research Program (VSRP) from KAUST.

Publisher
Institute of Electrical and Electronics Engineers (IEEE)

Conference/Event Name
2020 IEEE Congress on Evolutionary Computation (CEC)

DOI
10.1109/CEC48606.2020.9185648

arXiv
2002.00539

Additional Links
https://ieeexplore.ieee.org/document/9185648/
https://ieeexplore.ieee.org/document/9185648/
https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9185648

Relations
Is Supplemented By:

Permanent link to this record

Version History

Now showing 1 - 2 of 2
VersionDateSummary
2*
2020-09-17 11:50:17
Published with DOI, updated with accepted version
2020-02-26 08:54:37
* Selected version