Learning General Solutions through Multiple Evaluations during Development

Authors:
Tuan-Hao Hoang;R. I. Mckay;Daryl Essam;Xuan Hoai Nguyen
Affiliations:
Australian Defence Force Academy, University of New South Wales, Canberra, Australia ACT 2601;Structural Complexity Laboratory, Seoul National University, Seoul, Korea 151744;Australian Defence Force Academy, University of New South Wales, Canberra, Australia ACT 2601;Structural Complexity Laboratory, Seoul National University, Seoul, Korea 151744
Venue:
ICES '08 Proceedings of the 8th international conference on Evolvable Systems: From Biology to Hardware
Year:
2008

Citing 18
Cited 1

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Evolution of corridor following behavior in a noisy world

SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Machine Learning

Machine Learning
Shrinking the Genotype: L-systems for EHW?

ICES '01 Proceedings of the 4th International Conference on Evolvable Systems: From Biology to Hardware
Fighting Bloat with Nonparametric Parsimony Pressure

PPSN VII Proceedings of the 7th International Conference on Parallel Problem Solving from Nature
How artificial ontogenies can retard evolution

GECCO '05 Proceedings of the 7th annual workshop on Genetic and evolutionary computation
Evolutionary Design of Arbitrarily Large Sorting Networks Using Development

Genetic Programming and Evolvable Machines
Towards Development on a Silicon-based Cellular Computing Machine

Natural Computing: an international journal
Adding learning to the cellular development of neural networks: Evolution and the baldwin effect

Evolutionary Computation
Solving a real-world problem using an evolving heuristically driven schedule builder

Evolutionary Computation
Developmental evaluation in Genetic Programming: The TAG-based frame work

International Journal of Knowledge-based and Intelligent Engineering Systems - Genetic Programming An Emerging Engineering Tool
Ontogenetic programming

GECCO '96 Proceedings of the 1st annual conference on Genetic and evolutionary computation
Tree adjunct grammars

Journal of Computer and System Sciences
A developmental method for growing graphs and circuits

ICES'03 Proceedings of the 5th international conference on Evolvable systems: from biology to hardware
Building on success in genetic programming: adaptive variation and developmental evaluation

ISICA'07 Proceedings of the 2nd international conference on Advances in computation and intelligence
Developmental evaluation in genetic programming: the preliminary results

EuroGP'06 Proceedings of the 9th European conference on Genetic Programming
Genetic programming and evolutionary generalization

IEEE Transactions on Evolutionary Computation
Representation and structural difficulty in genetic programming

IEEE Transactions on Evolutionary Computation

Heterochronic scaling of developmental durations in evolved soft robots

Proceedings of the 15th annual conference on Genetic and evolutionary computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we investigate whether performing multiple evaluations during development --- a technique we call Evolutionary Developmental Evaluation (EDE) --- could help developmental Genetic Programming (GP) evolve general solutions, solving not only the original (training) problem, but also unseen similar problems (with higher degrees of complexity). The hypothesis is tested on two families of regression problems, and the experimental results support the hypothesis.