Skip to main content

Research Repository

Advanced Search

The Effect of Social Information Use without Learning on the Evolution of Behaviour (2021)
Journal Article
Channon. (2021). The Effect of Social Information Use without Learning on the Evolution of Behaviour. Artificial Life, 431-454. https://doi.org/10.1162/artl_a_00328

In a recent paper by Borg & Channon [6] it was shown that social information alone, decoupled from any within-lifetime learning, can result in improved performance on a food foraging task compared to when so13 cial information is unavailable. Here we... Read More about The Effect of Social Information Use without Learning on the Evolution of Behaviour.

A Simple 3D-Only Evolutionary Bipedal System with Albatross Morphology for Increased Performance (2020)
Journal Article
Channon. (2020). A Simple 3D-Only Evolutionary Bipedal System with Albatross Morphology for Increased Performance. IEEE Computational Intelligence Magazine, 125-132. https://doi.org/10.1109/SSCI47803.2020.9308500

Bipedal walking is a difficult behaviour to encode into an evolutionary neural network, particularly in three-dimensional environments. Agents must be constantly maintaining balance alongside their primary objectives. Here we re-implement a simple ev... Read More about A Simple 3D-Only Evolutionary Bipedal System with Albatross Morphology for Increased Performance.

Evolving developmental, recurrent and convolutional neural networks for deliberate motion planning in sparse reward tasks (2020)
Thesis
Jolley, B. P. Evolving developmental, recurrent and convolutional neural networks for deliberate motion planning in sparse reward tasks. (Thesis). Keele University. https://keele-repository.worktribe.com/output/417191

Motion planning algorithms have seen a diverse set of approaches in a variety of disciplines. In the domain of artificial evolutionary systems, motion planning has been included in models to achieve sophisticated deliberate behaviours. These algorith... Read More about Evolving developmental, recurrent and convolutional neural networks for deliberate motion planning in sparse reward tasks.

Maximum Individual Complexity is Indefinitely Scalable in Geb (2019)
Journal Article
Channon. (2019). Maximum Individual Complexity is Indefinitely Scalable in Geb. Artificial Life, 134-144. https://doi.org/10.1162/artl_a_00285

Geb was the first artificial life system to be classified as exhibiting open-ended evolutionary dynamics according to Bedau and Packard’s evolutionary activity measures and is the only one to have been classified as such according to the enhanced ve... Read More about Maximum Individual Complexity is Indefinitely Scalable in Geb.

Maximum Individual Complexity is Indefinitely Scalable in Geb (2019)
Journal Article
Channon. (2019). Maximum Individual Complexity is Indefinitely Scalable in Geb. Artificial Life, 134-144. https://doi.org/10.1162/artl_a_00285

Geb was the first artificial life system to be classified as exhibiting open-ended evolutionary dynamics according to Bedau and Packard’s evolutionary activity measures and is the only one to have been classified as such according to the enhanced ver... Read More about Maximum Individual Complexity is Indefinitely Scalable in Geb.

Evolving Robust, Deliberate Motion Planning With a Shallow Convolutional Neural Network (2018)
Journal Article
Channon. (2018). Evolving Robust, Deliberate Motion Planning With a Shallow Convolutional Neural Network. https://doi.org/10.1162/isal_a_00099

Deep Convolutional Neural Networks (ConvNets) have seen great success on machine learning tasks in recent years but have shown difficulty with tasks that require long-term deliberative planning. Whereas, purpose-built hybrid network architectures hav... Read More about Evolving Robust, Deliberate Motion Planning With a Shallow Convolutional Neural Network.

Toward Evolving Robust, Deliberate Motion Planning With HyperNEAT (2018)
Book Chapter
Channon, A., & Jolley, B. (2018). Toward Evolving Robust, Deliberate Motion Planning With HyperNEAT. In Proceedings of the IEEE Symposium Series on Computational Intelligence 2017 (3488 -3495)

Previous works have used a novel hybrid network architecture to create deliberative behaviours to solve increasingly challenging tasks in two-dimensional and threedimensional artificial worlds. At the foundation of each is a static hand-designed neur... Read More about Toward Evolving Robust, Deliberate Motion Planning With HyperNEAT.

Spontaneous mutation rate is a plastic trait associated with population density across domains of life. (2017)
Journal Article
Aston, E., McBain, A., Knight, C., Krašovec, R., Richards, H., Hatcher, C., Faulkner, K., Belavkin, R., Channon, A., & Gifford, D. (2017). Spontaneous mutation rate is a plastic trait associated with population density across domains of life. PLoS Biology, e2002731 - ?. https://doi.org/10.1371/journal.pbio.2002731

Rates of random, spontaneous mutation can vary plastically, dependent upon the environment. Such plasticity affects evolutionary trajectories and may be adaptive. We recently identified an inverse plastic association between mutation rate and populat... Read More about Spontaneous mutation rate is a plastic trait associated with population density across domains of life..

Open-Ended Evolution: Perspectives from the OEE1 Workshop in York (2016)
Journal Article
Channon. (2016). Open-Ended Evolution: Perspectives from the OEE1 Workshop in York. Artificial Life, 408-423. https://doi.org/10.1162/ARTL_a_00210

We describe the content and outcomes of the First Workshop on Open-Ended Evolution: Recent Progress and Future Milestones (OEE1), held during the ECAL 2015 conference at the University of York, UK, in July 2015. We briefly summarize the content of th... Read More about Open-Ended Evolution: Perspectives from the OEE1 Workshop in York.

Neuroevolution of Feedback Control for Object Manipulation by 3D Agents (2016)
Book Chapter
Stanton, A., & Channon, A. (2016). Neuroevolution of Feedback Control for Object Manipulation by 3D Agents. In Proceedings of the Artificial Life Conference 2016 (144-151)

Carlos Gershenson, Tom Froese, Jesus M. Siqueiros, Wendy Aguilar, Eduardo J. Izquierdo and Hiroki Sayama

Optimal mutation rate control under selection in hamming spaces (2015)
Presentation / Conference Contribution
Knight, C., Channon, A., Belavkin, R., Krasovec, R., & Aston, E. (2015, July). Optimal mutation rate control under selection in hamming spaces. Presented at Thirteenth European Conference on the Synthesis and Simulation of Living Systems (ECAL 2015), York

Where antibiotic resistance mutations meet quorum-sensing (2014)
Journal Article
Channon. (2014). Where antibiotic resistance mutations meet quorum-sensing. Microbial Cell, 250 - 252. https://doi.org/10.15698/mic2014.07.158

We do not need to rehearse the grim story of the global rise of antibiotic resistant microbes. But what if it were possible to control the rate with which antibiotic resistance evolves by de novo mutation? It seems that some bacteria may already do e... Read More about Where antibiotic resistance mutations meet quorum-sensing.

Testing the Variability Selection Hypothesis: The Adoption of Social Learning in Increasingly Variable Environments (2012)
Journal Article
Channon. (2012). Testing the Variability Selection Hypothesis: The Adoption of Social Learning in Increasingly Variable Environments. Artificial Life, 317 -324. https://doi.org/10.7551/978-0-262-31050-5-ch042

The variability selection hypothesis predicts the adoption of versatile behaviors and survival strategies, in response to increasingly variable environments. In hominin evolution the most apparent adaptation for versatility is the adoption of social... Read More about Testing the Variability Selection Hypothesis: The Adoption of Social Learning in Increasingly Variable Environments.

Critical mutation rate has an exponential dependence on population size (2011)
Book Chapter
Channon. (2011). Critical mutation rate has an exponential dependence on population size. In ECAL 2011 (117 -124)

Populations of individuals exist in a wide range of sizes, from billions of microorganisms to fewer than ten individuals in some critically endangered species. In any evolutionary system, there is significant evolutionary pressure to evolve sequences... Read More about Critical mutation rate has an exponential dependence on population size.

Discovering and maintaining behaviours inaccessible to incremental genetic evolution through transcription errors and cultural transmission (2011)
Book Chapter
Channon. (2011). Discovering and maintaining behaviours inaccessible to incremental genetic evolution through transcription errors and cultural transmission. In ECAL 2011 (101 -108). https://doi.org/10.7551/978-0-262-29714-1

In this work the question of whether the introduction of both transcription errors and cultural transmission, in the form of learning by imitation, can enable the evolution of behaviours inaccessible to incremental genetic evolution alone is assessed... Read More about Discovering and maintaining behaviours inaccessible to incremental genetic evolution through transcription errors and cultural transmission.

Neuroevolution of agents capable of reactive and deliberative behaviours in novel and dynamic environments (2007)
Journal Article
Channon. (2007). Neuroevolution of agents capable of reactive and deliberative behaviours in novel and dynamic environments. Lecture notes in computer science, 345 - 354. https://doi.org/10.1007/978-3-540-74913-4_35

Both reactive and deliberative qualities are essential for a good action selection mechanism. We present a model that embodies a hybrid of two very different neural network architectures inside an animat: one that controls their high level deliberati... Read More about Neuroevolution of agents capable of reactive and deliberative behaviours in novel and dynamic environments.