A Taxonomy for Artificial Embryogeny

  title={A Taxonomy for Artificial Embryogeny},
  author={Kenneth O. Stanley and Risto Miikkulainen},
  journal={Artificial Life},
A major challenge for evolutionary computation is to evolve phenotypes such as neural networks, sensory systems, or motor controllers at the same level of complexity as found in biological organisms. In order to meet this challenge, many researchers are proposing indirect encodings, that is, evolutionary mechanisms where the same genes are used multiple times in the process of building a phenotype. Such gene reuse allows compact representations of very complex phenotypes. Development is a… 

Artificial Ontogenies: A Computational Model of the Control and Evolution of Development

A network-lineage model of artificial ontogenies is described that incorporates a developmental mapping between the dynamics of a gene network and a cell lineage representation of a phenotype, suggesting that the levels of ontogenetic complexity observed in biological organisms may be a product of the network architecture of developmental control.

Evolutionary morphogenesis for multi-cellular systems

The morphogenetic system shows better scalability compared to a direct genetic encoding in the evolution of structures of differentiated cells, and its dynamics provides fault-tolerance up to high fault rates.

Evolutionary Growth of Genome Representations on Artificial Cellular Organisms with Indirect Encodings

This work investigates an incremental evolutionary growth of genomes without any a priori knowledge on the necessary genotype size by means of gene duplication, allowing the evolution of scalable genomes that are able to adapt genetic information content while compactness and efficiency are retained.

Evolutionary growth of genomes for the development and replication of multicellular organisms with indirect encoding

It is argued that artificial genomes may also grow in size during evolution to produce high-dimensional solutions incrementally and results show that the proposed evolutionary growth of genomes' method is able to produce compact and effective genomes, without the need of specifying the full set of regulatory configurations.

Evolutionary Development based on Genetic Regulatory Models for Behavior-Finding

Supporting the latest biological hypothesis, the findings show that the sole variation in the regulation of gene expression is indeed a sufficient condition for the evolutionary emergence of novelty and diversity.

Evolutionary Design in Embryogeny

Computational embryogeny is the study of representations for evolutionary computation that mimic biological embryogenic representations, which contain analogs to the complex biological processes that steer a single cell to become a rose, a mouse, or a man.

Artificial evolutionary development

The developmental process can be seen as a genotype-to-phenotype mapping, and it is possible to describe development detached from the optimization method as a black-box that has a vector of object variables as input, and returns a spatial distribution of cells ready for evaluation.

Evolutionary development of tensegrity structures

Behavior-Finding: Morphogenetic Designs Shaped by Function

This chapter discusses evolutionary morphogenetic algorithms inspired by these important aspects of biological evolution that could contribute to the automation of processes that design “organic” structures, whose morphologies and controllers are intended to solve a functional problem.

Computer Morphogenesis in Self-Organizing Structures

This paper presents the development of a model that tries to emulate the biological cells and to take advantage of some of their characteristics by trying to adapt them to artificial cells.



A Developmental Model for the Evolution of Artificial Neural Networks

This work presents a model of decentralized growth and development for artificial neural networks (ANNs), inspired by developmental biology and the physiology of nervous systems, and demonstrates the power of the artificial chemistry by analyzing engineered genomes that lead to the growth of simple networks with behaviors known from physiology.

Cell division and migration in a ‘genotype’ for neural networks

This paper presents a model of neural development which includes cell division and cell migration in addition to axonal growth and branching, and finds that mutations that affect different phases of development have very different evolutionary consequences.

Repeated structure and dissociation of genotypic and phenotypic complexity in artificial ontogeny

It is demonstrated that evolved genetic regulatory networks in AO give rise to hierarchical, repeated phenotypic structures, and the claim that artificial ontogeny is a useful design tool for the evolutionary design of virtual agents and real-world robots is supported.

Toward an evolvable model of development for autonomous agent synthesis

A simplified yet biologically defensible model of the developmental process of autonomous agents, specifically one that has agent-like properties is presented and it is demonstrated that this developmental model can be evolved.

A Gene Network Model for Developing Cell Lineages

A dynamic recurrent gene network (DRGN) model was designed and its ability to control the developmental trajectories of cells during embryogenesis was evaluated, demonstrating the ability of DRGNs to perform the tasks with minimal external input.

From Evolutionary Computation to Computational Evolution

It is proposed that evolutionary computation be understood more like computational evolution, i.e., to use the evolutionary process for construction, rather than for optimization, and to construct intelligence as adaptive behavior based on artiicial neural networks.

A connectionist model of development.

Three Ways to Grow Designs: A Comparison of Embryogenies for an Evolutionary Design Problem

The results are surprising, with the implicit embryogeny outperforming all other techniques by showing no significant increase in the size of the genotypes or decrease in accuracy of evolution as the scale of the problem is increased.