A Taxonomy for Artificial Embryogeny

By Kenneth O. Stanley, Risto Miikkulainen. 2003

507 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Mechanical Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Mechanical Engineering

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “This review focuses on evolution and learning, but less on artiﬁcial developmental systems (Stanley and Miikkulainen, 2003b) because development may occur independently of, or dependent upon, external factors.”
Evolutionary Computation for Reinforcement Learning (2012, background): “Generative and developmental systems (Gruau, 1994; Hornby and Pollack, 2002; Stanley and Miikkulainen, 2003; Stanley et al, 2009) is a subfield of evolutionary computation that focuses on evolving indirect encodings.”
A novel generative encoding for exploiting neural network sensor and output geometry (2007, background): “The aim is to find the right abstraction of natural development for a computer running an evolutionary algorithm, so that EC can begin to discover complexity on a natural scale [19].”
Ieee Transactions on Evolutionary Computation on the Performance of Indirect Encoding across the Continuum of Regularity (unknown): “In contrast, regularities are common with indirect encodings (also known as generative or developmental encodings), wherein information in the genome can be reused to affect many parts of the phenotype [2].”
Quality Diversity: A New Frontier for Evolutionary Computation (2016, background): “Yet the ability of such algorithms to match the complexity and sophistication of nature has frustratingly lagged, as researchers in the fields often observe (Stanley and Miikkulainen, 2003; Doncieux et al., 2015).”
Generative NeuroEvolution for Deep Learning (2013, background): “That is, information is reused in such an encoding, which is a major focus in the field of GDS from which HyperNEAT originates [27, 28].”
Revising the evolutionary computation abstraction: minimal criteria novelty search (2010, background): “The topic of complexity in natural evolution is debated across biology, artificial life, and evolutionary computation [4, 12, 18, 20, 21, 24, 33].”
Neuroevolution (2010, background): “Indirect encoding, in contrast, specifies a process through which the network is constructed, such as cell division or generation through a grammar [5, 8, 17, 21].”
AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence (2019, background): “That includes research into encodings (aka representations) [168, 171, 170, 203, 55], search operators, and the production of architectures that are regular [171, 27, 69], modular [28, 69], and hierarchical [109].”
Supplementing evolutionary developmental systems with abstract models of neurogenesis (2007, background): “Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for pro.t or commercial advantage and that copies bear this notice and the full citation on the .rst page.”
Indirectly Encoding Neural Plasticity as a Pattern of Local Rules (2010, methodology): “interest has grown in recent years in indirectly encoding the weights of ANNs so that they can be discovered as patterns [4–9], the power of indirect encoding is rarely applied to encoding learning rules.”
Exploiting Open-Endedness to Solve Problems Through the Search for Novelty (2008, background): “The topic of complexity in natural evolution is much in contention across biology, artificial life, and evolutionary computation [15, 19, 23, 28].”
Unshackling evolution: evolving soft robots with multiple materials and a powerful generative encoding (2013, background): “Categories and Sub ject Descriptors: I.2.11 [Distributed Arti.cial Intelligence]:Intelligent Agents General Terms: Algorithms, Design, Experimentation Keywords: Genetic Algorithms, Generative Encodings, CPPN-NEAT, Soft-Robotics, HyperNEAT, Evolving Morphologies Permission to make digital or hard…”
The road to everywhere : Evolution, complexity and progress in natural and artificial systems (2008, background): “Stanley and Miikkulainen [172] provide an enlightening review and discussion of developmental systems in artificial evolution.”