Search Results for author: Larry Bull

Found 40 papers, 1 papers with code

Toward Neuromic Computing: Neurons as Autoencoders

no code implementations4 Mar 2024 Larry Bull

This short paper presents the idea that neural backpropagation is using dendritic processing to enable individual neurons to perform autoencoding.

Exploring the Unexplored: Understanding the Impact of Layer Adjustments on Image Classification

no code implementations25 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.

Image Classification

Evolving Diploid Boolean and Multi-Valued Gene Networks

no code implementations19 Nov 2023 Larry Bull

Boolean networks have been widely used to explore aspects of gene regulation, traditionally with a single network.

On Cooperative Coevolution and Global Crossover

no code implementations12 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.

Coevolving Boolean and Multi-Valued Regulatory Networks

no code implementations3 Feb 2023 Larry Bull

Random Boolean networks have been used widely to explore aspects of gene regulatory networks.

Deep Learning with a Classifier System: Initial Results

no code implementations1 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.

Handwritten Digit Recognition

On Sexual Selection

no code implementations23 Feb 2021 Larry Bull

Sexual selection is a fundamental aspect of evolution for all eukaryotic organisms with mating types.

Evolving Nano Particle Cancer Treatments with Multiple Particle Types

no code implementations10 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.

Evolutionary Algorithms

Are Artificial Dendrites useful in NeuroEvolution?

no code implementations2 Oct 2020 Larry Bull

The significant role of dendritic processing within neuronal networks has become increasingly clear.

On the Baldwin Effect under Coevolution

no code implementations29 Apr 2020 Larry Bull

The potentially beneficial interaction between learning and evolution, the Baldwin effect, has long been established.

Exploring Distributed Control with the NK Model

no code implementations20 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.

Decision Making

Novelty search employed into the development of cancer treatment simulations

no code implementations21 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.

Utilizing Differential Evolution into optimizing targeted cancer treatments

no code implementations21 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.

Attribute

Haploid-Diploid Evolution: Nature's Memetic Algorithm

no code implementations13 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.

Autoencoding with a Classifier System

no code implementations23 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.

Dimensionality Reduction

Autoencoding with a Learning Classifier System: Initial Results

no code implementations26 Jul 2019 Larry Bull

Autoencoders enable data dimensionality reduction and a key component of many (deep) learning systems.

Clustering Dimensionality Reduction

A Simple Haploid-Diploid Evolutionary Algorithm

no code implementations27 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.

Sex and Coevolution

no code implementations15 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.

Towards an Evolvable Cancer Treatment Simulator

no code implementations19 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.

Evolutionary Algorithms Two-sample testing

Towards the Design of Aerostat Wind Turbine Arrays through AI

no code implementations13 Nov 2018 Larry Bull, Neil Phillips

A new form of aerostat wind generation system which contains an array of interacting turbines is proposed.

The Evolution of Gene Dominance through the Baldwin Effect

no code implementations8 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.

The Evolution of Sex Chromosomes through the Baldwin Effect

no code implementations10 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.

Design Mining Microbial Fuel Cell Cascades

no code implementations18 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.

Haploid-Diploid Evolutionary Algorithms

no code implementations19 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.

Evolutionary Algorithms

The Evolution of Sex through the Baldwin Effect

no code implementations1 Jul 2016 Larry Bull

This paper suggests that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect.

Evolving Boolean Regulatory Networks with Variable Gene Expression Times

no code implementations2 Mar 2016 Larry Bull

The time taken for gene expression varies not least because proteins vary in length considerably.

Evolving Unipolar Memristor Spiking Neural Networks

no code implementations1 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.

A Cognitive Architecture Based on a Learning Classifier System with Spiking Classifiers

no code implementations31 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.

reinforcement-learning Reinforcement Learning (RL)

On Design Mining: Coevolution and Surrogate Models

no code implementations29 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.

Attribute

Evolving Spiking Networks with Variable Resistive Memories

no code implementations17 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.

Evolving Boolean Networks with RNA Editing

no code implementations8 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.

Design Mining Interacting Wind Turbines

no code implementations2 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.

Evolutionary Algorithms

A Brief History of Learning Classifier Systems: From CS-1 to XCS

no code implementations15 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.

Towards Application of the RBNK Model

no code implementations21 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.

Toward the Coevolution of Novel Vertical-Axis Wind Turbines

no code implementations13 Aug 2013 Richard J. Preen, Larry Bull

The production of renewable and sustainable energy is one of the most important challenges currently facing mankind.

Evolving Boolean Regulatory Networks with Epigenetic Control

no code implementations20 Jun 2013 Larry Bull

The significant role of epigenetic mechanisms within natural systems has become increasingly clear.

Discrete Dynamical Genetic Programming in XCS

no code implementations18 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.

Towards the Evolution of Vertical-Axis Wind Turbines using Supershapes

1 code implementation18 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.

3D Shape Representation Evolutionary Algorithms

Discrete and fuzzy dynamical genetic programming in the XCSF learning classifier system

no code implementations26 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.