Multilayer feedforward networks are universal approximators
Neural Networks
Genetic micro programming of neural networks
Advances in genetic programming
SIGGRAPH '94 Proceedings of the 21st annual conference on Computer graphics and interactive techniques
Genetic algorithms + data structures = evolution programs (3rd ed.)
Genetic algorithms + data structures = evolution programs (3rd ed.)
A new kind of science
Evolving neural networks through augmenting topologies
Evolutionary Computation
Proceedings of the European Conference on Genetic Programming
A Taxonomy for artificial embryogeny
Artificial Life
Bias and scalability in evolutionary development
GECCO '05 Proceedings of the 7th annual conference on Genetic and evolutionary computation
Investigations Into Graceful Degradation of Evolutionary Developmental Software
Natural Computing: an international journal
Why are evolved developing organisms also fault-tolerant?
SAB'06 Proceedings of the 9th international conference on From Animals to Animats: simulation of Adaptive Behavior
A Multi-cellular Developmental System in Continuous Space Using Cell Migration
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Supervised and Evolutionary Learning of Echo State Networks
Proceedings of the 10th international conference on Parallel Problem Solving from Nature: PPSN X
A model for intrinsic artificial development featuring structural feedback and emergent growth
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Open-ended on-board evolutionary robotics for robot swarms
CEC'09 Proceedings of the Eleventh conference on Congress on Evolutionary Computation
Unsupervised learning of echo state networks: a case study in artificial embryogeny
EA'07 Proceedings of the Evolution artificielle, 8th international conference on Artificial evolution
Image compression of natural images using artificial gene regulatory networks
Proceedings of the 12th annual conference on Genetic and evolutionary computation
| Hi-index | 0.00 |
This paper introduces a continuous model for Multi-cellular Developmental Design. The cells are fixed on a 2D grid and exchange "chemicals" with their neighbors during the growth process. The quantity of chemicals that a cell produces, as well as the differentiation value of the cell in the phenotype, are controlled by a Neural Network (the genotype) that takes as inputs the chemicals produced by the neighboring cells at the previous time step. In the proposed model, the number of iterations of the growth process is not pre-determined, but emerges during evolution: only organisms for which the growth process stabilizes give a phenotype (the stable state), others are declared nonviable. The optimization of the controller is done using the NEAT algorithm, that optimizes both the topology and the weights of the Neural Networks. Though each cell only receives local information from its neighbors, the experimental results of the proposed approach on the 'flags' problems (the phenotype must match a given 2D pattern) are almost as good as those of a direct regression approach using the same model with global information. Moreover, the resulting multi-cellular organisms exhibit almost perfect self-healing characteristics.