Skip to main content

Research Repository

Advanced Search

Alastair Channon's Outputs (12)

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.

Critical Mutation Rate in a Population with Horizontal Gene Transfer (2017)
Book Chapter
Channon. (2017). Critical Mutation Rate in a Population with Horizontal Gene Transfer. In Proceedings of ECAL 2017: the 14th European Conference on Artificial Life (446-453). https://doi.org/10.7551/ecal_a_074

Horizontal gene transfer (HGT) enables segments of DNA to be transferred between individuals in a population in addition to from parent to child. It is a prominent process in bacterial reproduction. Existing in silico models have succeeded in predict... Read More about Critical Mutation Rate in a Population with Horizontal Gene Transfer.

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

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.

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.

Analysing co-evolution among artificial 3D creatures (2006)
Book Chapter
Channon. (2006). Analysing co-evolution among artificial 3D creatures. In Lecture Notes in Computer Science (167 -178)

This paper is concerned with the analysis of coevolutionary dynamics among 3D artificial creatures, similar to those introduced by Sims (1). Coevolution is subject to complex dynamics which are notoriously difficult to analyse. We introduce an improv... Read More about Analysing co-evolution among artificial 3D creatures.

A virtual creatures model for studies in artificial evolution (2005)
Book Chapter
Channon. (2005). A virtual creatures model for studies in artificial evolution. In 2005 IEEE Congress on Evolutionary Computation, vols 1-3, proceedings (565 -572)

We present the results of our replication of Karl Sims' work on the evolution of artificial creatures in a physically realistic 3D environment. We used standard McCulloch-Pitts neurons instead of a more complex set of ad hoc neurons, which we believe... Read More about A virtual creatures model for studies in artificial evolution.

Improving and still passing the ALife test: Component-normalised activity statistics classify evolution in Geb as unbounded (2003)
Book Chapter
Channon. (2003). Improving and still passing the ALife test: Component-normalised activity statistics classify evolution in Geb as unbounded. In Artificial Life VIII: proceedings of the Eighth International Conference on Artificial Life (173 -181)

Bedau, Snyder & Packard’s (1998) classification system for long-term evolutionary dynamics provides a test for openended evolution. Making this ALife test more rigorous, and passing it, are two of the most important open problems in the field. Previo... Read More about Improving and still passing the ALife test: Component-normalised activity statistics classify evolution in Geb as unbounded.

Passing the ALife test: activity statistics classify evolution in Geb as unbounded (2001)
Book Chapter
Channon. (2001). Passing the ALife test: activity statistics classify evolution in Geb as unbounded. In Advances in Artificial Life (417 - 426)

Bedau and Packard’s evolutionary activity statistics [1, 2] are used to classify the evolutionary dynamics in Geb [3, 4], a system designed to verify and extend theories behind the generation of evolutionary emergent systems. The result is that, acco... Read More about Passing the ALife test: activity statistics classify evolution in Geb as unbounded.

Perpetuating evolutionary emergence (1998)
Book Chapter
Channon. (1998). Perpetuating evolutionary emergence. In From Animals to Animats 5: Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior (SAB98), Zurich (534 -539)

Perpetuating evolutionary emergence is the key to artificially evolving increasingly complex systems. In order to generate complex entities with adaptive behaviors beyond our manual design capability, longterm incremental evolution with continuing em... Read More about Perpetuating evolutionary emergence.