All Outputs (279)

Exploring filter placement in convolutional layer topologies based on ResNet for image classification (2025)
Journal Article

In this paper we investigate the impact that altering the convolutional layer topology has upon the performance of computer vision tasks using a variety of widely used benchmark image datasets. Despite the widespread convention in convolutional neura... Read More about Exploring filter placement in convolutional layer topologies based on ResNet for image classification.

ResNet18 performance: Impact of network depth and image resolution on image classification (2025)
Presentation / Conference Contribution

This study explores aspects of using ResNet18 for the classification of biomedical images, using the 2D medical images from the MedMNIST library that is widely used for benchmarking. The number of layers within the ResNet18 was studied. The typically... Read More about ResNet18 performance: Impact of network depth and image resolution on image classification.

Examining neural networks through architectural variation analysis for image classification (2025)
Presentation / Conference Contribution

This paper presents a method for examining neural networks in image classification through architectural variation analysis. Small-scale experiments generate initial insights, and the configurations are further tested on entire datasets. The newly pr... Read More about Examining neural networks through architectural variation analysis for image classification.

Neurons as autoencoders (2024)
Journal Article

This letter presents the idea that neural backpropagation is exploiting dendritic processing to enable individual neurons to perform autoencoding. Using a very simple connection weight search heuristic and artificial neural network model, the effects... Read More about Neurons as autoencoders.

On recombination (2024)
Journal Article

The predominant explanations for the inclusion of chromosomal recombination during meiosis are either that it serves as a mechanism for repair or for increased adaptability. However, neither gives a clear immediate selective advantage to the reproduc... Read More about On recombination.

On Cooperative Coevolution and Global Crossover (2024)
Journal Article

Cooperative coevolutionary algorithms (CCEAs) divide a given problem in to a number of subproblems and use an evolutionary algorithm to solve each subproblem. This letter is concerned with the scenario under which a single fitness measure exists. By... Read More about On Cooperative Coevolution and Global Crossover.

Evolving multi-valued regulatory networks on tuneable fitness landscapes (2023)
Journal Article

Random Boolean networks have been used widely to explore aspects of gene regulatory networks. As the name implies, traditionally the model has used a binary representation scheme. This paper uses a modified form of the model to systematically explore... Read More about Evolving multi-valued regulatory networks on tuneable fitness landscapes.

A systematic review of machine-learning solutions in anaerobic digestion (2023)
Journal Article

The use of machine learning (ML) in anaerobic digestion (AD) is growing in popularity and improves the interpretation of complex system parameters for better operation and optimisation. This systematic literature review aims to explore how ML is curr... Read More about A systematic review of machine-learning solutions in anaerobic digestion.

A generalised dropout mechanism for distributed systems (2022)
Journal Article

This letter uses a modified form of the NK model introduced to explore aspects of distributed control. In particular, a previous result suggesting the use of dynamically formed subgroups within the overall system can be more effective than global con... Read More about A generalised dropout mechanism for distributed systems.

A haploid-diploid evolutionary algorithm optimizing nanoparticle based cancer treatments (2022)
Book Chapter

This paper uses a recent explanation for the fundamental haploid-diploid lifecycle of eukaryotic organisms to present a new evolutionary algorithm that differs from all previous known work using diploid representations. A form of the Baldwin effect h... Read More about A haploid-diploid evolutionary algorithm optimizing nanoparticle based cancer treatments.

Nonbinary representations in the NK and NKCS models (2022)
Journal Article

The NK model has been used widely to explore aspects of natural evolution and complex systems. Traditionally, the model has used a binary representation scheme. This paper introduces a modified form of the NK model through which to systematically exp... Read More about Nonbinary representations in the NK and NKCS models.

Evolving Boolean regulatory networks with variable gene expression times (2021)
Book Chapter

The time taken for gene expression varies not least because proteins vary in length considerably. This paper uses an abstract, tuneable Boolean regulatory network model to explore gene expression time variation. In particular, it is shown how non-uni... Read More about Evolving Boolean regulatory networks with variable gene expression times.

Evolutionary algorithms designing nanoparticle cancer treatments with multiple particle types (2021)
Journal Article

There is a rich history of evolutionary algorithms tackling optimization problems where the most appropriate size of solutions, namely the genome length, is unclear a priori. Here, we investigated the applicability of this methodology on the problem... Read More about Evolutionary algorithms designing nanoparticle cancer treatments with multiple particle types.

On coevolution: Asymmetry in the NKCS model (2021)
Journal Article

The NKCS model was introduced to explore coevolutionary systems, that is, systems in which multiple species are closely interconnected. The fitness landscapes of the species are coupled to a controllable amount, where the underlying properties of the... Read More about On coevolution: Asymmetry in the NKCS model.

On the emergence of intersexual selection: Arbitrary trait preference improves female-male coevolution (2021)
Journal Article

Sexual selection is a fundamental aspect of evolution for all eukaryotic organisms with mating types. This article suggests intersexual selection is best viewed as a mechanism with which to compensate for the unavoidable dynamics of coevolution betwe... Read More about On the emergence of intersexual selection: Arbitrary trait preference improves female-male coevolution.

Autoencoding with a classifier system (2021)
Journal Article

Autoencoders are data-specific compression algorithms learned automatically from examples. The predominant approach has been to construct single large global models that cover the domain. However, training and evaluating models of increasing size com... Read More about Autoencoding with a classifier system.

Are artificial dendrites useful in neuro-evolution? (2021)
Journal Article

The significant role of dendritic processing within neuronal networks has become increasingly clear. This letter explores the effects of including a simple dendrite-inspired mechanism into neuro-evolution. The phenomenon of separate dendrite activati... Read More about Are artificial dendrites useful in neuro-evolution?.

Metameric representations on optimization of nano particle cancer treatment (2021)
Journal Article

In silico evolutionary optimization of cancer treatment based on multiple nano-particle (NP) assisted drug delivery systems was investigated in this study. The use of multiple types of NPs is expected to increase the robustness of the treatment, due... Read More about Metameric representations on optimization of nano particle cancer treatment.

Supplementary material: Evolutionary algorithms designing nano particle cancer treatments with multiple particle types (2021)
Other

Supplementary material: Evolutionary algorithms designing nano particle cancer treatments with multiple particle types

The Evolution of Complexity: Simple Simulations of Major Innovations (2020)
Book