no code implementations • 4 Mar 2024 • Larry Bull
This short paper presents the idea that neural backpropagation is using dendritic processing to enable individual neurons to perform autoencoding.
no code implementations • 25 Jan 2024 • Haixia Liu, Tim Brailsford, James Goulding, Gavin Smith, Larry Bull
This paper investigates how adjustments to deep learning architectures impact model performance in image classification.
no code implementations • 19 Nov 2023 • Larry Bull
Boolean networks have been widely used to explore aspects of gene regulation, traditionally with a single network.
no code implementations • 12 Aug 2023 • Larry Bull, Haixia Liu
Cooperative coevolutionary algorithms (CCEAs) divide a given problem in to a number of subproblems and use an evolutionary algorithm to solve each subproblem.
no code implementations • 3 Feb 2023 • Larry Bull
Random Boolean networks have been used widely to explore aspects of gene regulatory networks.
no code implementations • 1 Mar 2021 • Richard J. Preen, Larry Bull
This article presents the first results from using a learning classifier system capable of performing adaptive computation with deep neural networks.
no code implementations • 23 Feb 2021 • Larry Bull
Sexual selection is a fundamental aspect of evolution for all eukaryotic organisms with mating types.
no code implementations • 10 Nov 2020 • Michail-Antisthenis Tsompanas, Larry Bull, Andrew Adamatzky, Igor Balaz
Utilizing a treatment comprising of multiple types of NPs is expected to be more effective due to the higher complexity of the treatment.
no code implementations • 2 Oct 2020 • Larry Bull
The significant role of dendritic processing within neuronal networks has become increasingly clear.
no code implementations • 29 Apr 2020 • Larry Bull
The potentially beneficial interaction between learning and evolution, the Baldwin effect, has long been established.
no code implementations • 20 Apr 2020 • Larry Bull
Initial results show how varying the size and underlying functional structure of a given system affects the performance of different distributed control structures and decision making, including within dynamically formed structures and those with differing numbers of control nodes.
no code implementations • 21 Mar 2020 • Michail-Antisthenis Tsompanas, Larry Bull, Andrew Adamatzky, Igor Balaz
Conventional optimization methodologies may be hindered when the automated search is stuck into local optima because of a deceptive objective function landscape.
no code implementations • 21 Mar 2020 • Michail-Antisthenis Tsompanas, Larry Bull, Andrew Adamatzky, Igor Balaz
Working towards the development of an evolvable cancer treatment simulator, the investigation of Differential Evolution was considered, motivated by the high efficiency of variations of this technique in real-valued problems.
no code implementations • 13 Nov 2019 • Michail-Antisthenis Tsompanas, Larry Bull, Andrew Adamatzky, Igor Balaz
This paper uses a recent explanation for the fundamental haploid-diploid lifecycle of eukaryotic organisms to present a new memetic algorithm that differs from all previous known work using diploid representations.
no code implementations • 23 Oct 2019 • Richard J. Preen, Stewart W. Wilson, Larry Bull
Learning classifier systems (LCS) are a framework for adaptively subdividing input spaces into an ensemble of simpler local approximations that together cover the domain.
no code implementations • 26 Jul 2019 • Larry Bull
Autoencoders enable data dimensionality reduction and a key component of many (deep) learning systems.
no code implementations • 27 Mar 2019 • Larry Bull
It has recently been suggested that evolution exploits a form of fitness landscape smoothing within eukaryotic sex due to the haploid-diploid cycle.
no code implementations • 15 Mar 2019 • Larry Bull
It has been suggested that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect.
no code implementations • 19 Dec 2018 • Richard J. Preen, Larry Bull, Andrew Adamatzky
The use of high-fidelity computational simulations promises to enable high-throughput hypothesis testing and optimisation of cancer therapies.
no code implementations • 13 Nov 2018 • Larry Bull, Neil Phillips
A new form of aerostat wind generation system which contains an array of interacting turbines is proposed.
no code implementations • 8 Nov 2018 • Larry Bull
It has recently been suggested that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect.
no code implementations • 10 Aug 2018 • Larry Bull
It has recently been suggested that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect.
no code implementations • 18 Oct 2016 • Richard J. Preen, Jiseon You, Larry Bull, Ioannis A. Ieropoulos
Microbial fuel cells (MFCs) perform wastewater treatment and electricity production through the conversion of organic matter using microorganisms.
no code implementations • 19 Aug 2016 • Larry Bull
This paper uses the recent idea that the fundamental haploid-diploid lifecycle of eukaryotic organisms implements a rudimentary form of learning within evolution.
no code implementations • 1 Jul 2016 • Larry Bull
This paper suggests that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect.
no code implementations • 2 Mar 2016 • Larry Bull
The time taken for gene expression varies not least because proteins vary in length considerably.
no code implementations • 1 Sep 2015 • David Howard, Larry Bull, Ben De Lacy Costello
Neuromorphic computing --- brainlike computing in hardware --- typically requires myriad CMOS spiking neurons interconnected by a dense mesh of nanoscale plastic synapses.
no code implementations • 31 Aug 2015 • David Howard, Larry Bull, Pier-Luca Lanzi
Learning Classifier Systems (LCS) are population-based reinforcement learners that were originally designed to model various cognitive phenomena.
no code implementations • 29 Jun 2015 • Richard J. Preen, Larry Bull
Design mining is the use of computational intelligence techniques to iteratively search and model the attribute space of physical objects evaluated directly through rapid prototyping to meet given objectives.
no code implementations • 17 May 2015 • Gerard David Howard, Larry Bull, Ben De Lacy Costello, Andrew Adamatzky, Ella Gale
Variable resistive memories are the focus of this research; each synapse has its own conductance profile which modifies the plastic behaviour of the device and may be altered during evolution.
no code implementations • 8 May 2015 • Larry Bull
The editing of transcribed RNA by other molecules such that the form of the final product differs from that specified in the corresponding DNA sequence is ubiquitous.
no code implementations • 2 Oct 2014 • Richard J. Preen, Larry Bull
The accuracy of various modelling algorithms used to estimate the fitness of evaluated individuals from the initial experiments is compared.
no code implementations • 15 Jan 2014 • Larry Bull
Modern Learning Classifier Systems can be characterized by their use of rule accuracy as the utility metric for the search algorithm(s) discovering useful rules.
no code implementations • 10 Jan 2014 • Larry Bull
Modern learning classifier systems typically exploit a niched genetic algorithm to facilitate rule discovery.
no code implementations • 21 Oct 2013 • Larry Bull
The computational modeling of genetic regulatory networks is now common place, either by fitting a system to experimental data or by exploring the behaviour of abstract systems with the aim of identifying underlying principles.
no code implementations • 13 Aug 2013 • Richard J. Preen, Larry Bull
The production of renewable and sustainable energy is one of the most important challenges currently facing mankind.
no code implementations • 20 Jun 2013 • Larry Bull
The significant role of epigenetic mechanisms within natural systems has become increasingly clear.
no code implementations • 18 Apr 2012 • Richard J. Preen, Larry Bull
A number of representation schemes have been presented for use within Learning Classifier Systems, ranging from binary encodings to neural networks.
1 code implementation • 18 Apr 2012 • Richard J. Preen, Larry Bull
We have recently presented an initial study of evolutionary algorithms used to design vertical-axis wind turbines (VAWTs) wherein candidate prototypes are evaluated under approximated wind tunnel conditions after being physically instantiated by a 3D printer.
no code implementations • 26 Jan 2012 • Richard J. Preen, Larry Bull
A number of representation schemes have been presented for use within learning classifier systems, ranging from binary encodings to neural networks.