arXiv subjects

Larry Bull

Publications and source records attributed to Larry Bull.

At least 19 recordsLinked to original sources

arXiv2024

An NKCS Model of Bookchins Communalism

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 individual landscapes are also controllable. No previous work has explored the use of hierarchical control within the model. This paper explores the effects of using a confederation, based on Bookchins communalism, and a single point of global control. Significant changes in behaviour from the traditional model are seen across the parameter space.

cs.NE↗

arXiv2024

Toward Neuromic Computing: Neurons as Autoencoders

This short paper presents the idea that neural backpropagation is using dendritic processing to enable individual neurons to perform autoencoding. Using a very simple connection weight search heuristic and artificial neural network model, the effects of interleaving autoencoding for each neuron in a hidden layer of a feedforward network are explored. This is contrasted to the standard layered approach to autoencoding. It is shown that such individualised processing is not detrimental and can improve network learning.

cs.NE↗

arXiv2024

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

This paper investigates how adjustments to deep learning architectures impact model performance in image classification. Small-scale experiments generate initial insights although the trends observed are not consistent with the entire dataset. Filtering operations in the image processing pipeline are crucial, with image filtering before pre-processing yielding better results. The choice and order of layers as well as filter placement significantly impact model performance. This study provides valuable insights into optimizing deep learning models, with potential avenues for future research including collaborative platforms.

cs.CV↗

arXiv2024

On Cooperative Coevolution and Global Crossover

Cooperative coevolutionary algorithms (CCEAs) divide a given problem in to a number of subproblems and use an evolutionary algorithm to solve each subproblem. This short paper is concerned with the scenario under which only a single, global fitness measure exists. By removing the typically used subproblem partnering mechanism, it is suggested that such CCEAs can be viewed as making use of a generalised version of the global crossover operator introduced in early Evolution Strategies. Using the well-known NK model of fitness landscapes, the effects of varying aspects of global crossover with respect to the ruggedness of the underlying fitness landscape are explored. Results suggest improvements over the most widely used form of CCEAs, something further demonstrated using other well-known test functions.

cs.NE↗

arXiv2023

Evolving Diploid Boolean and Multi-Valued Gene Networks

Boolean networks have been widely used to explore aspects of gene regulation, traditionally with a single network. A modified form of the model to explore the effects of increasing the number of gene states has also recently been introduced. In this paper, these discrete dynamical networks are evolved as diploids within rugged fitness landscapes to explore their behaviour. Results suggest the general properties of haploid networks in similar circumstances remain for diploids. The previously proposed inherent fitness landscape smoothing properties of eukaryotic sex are shown to be exhibited in these dynamical systems, as is their propensity to change in size based upon the characteristics of the network and fitness landscape.

q-bio.MN↗

arXiv2023

Coevolving Boolean and Multi-Valued Regulatory Networks

Random Boolean networks have been used widely to explore aspects of gene regulatory networks. A modified form of the model through which to systematically explore the effects of increasing the number of gene states has previously been introduced. In this paper, these discrete dynamical networks are coevolved within coupled, rugged fitness landscapes to explore their behaviour. Results suggest the general properties of the Boolean model remain with higher valued logic regardless of the update scheme or fitness sampling method. Introducing topological asymmetry in the coevolving networks is seen to alter behaviour.

q-bio.MN↗

arXiv2021

Autoencoding with a Classifier System

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 comes at the price of additional time and computational cost. Conditional computation, sparsity, and model pruning techniques can reduce these costs while maintaining performance. Learning classifier systems (LCS) are a framework for adaptively subdividing input spaces into an ensemble of simpler local approximations that together cover the domain. LCS perform conditional computation through the use of a population of individual gating/guarding components, each associated with a local approximation. This article explores the use of an LCS to adaptively decompose the input domain into a collection of small autoencoders where local solutions of different complexity may emerge. In addition to benefits in convergence time and computational cost, it is shown possible to reduce code size as well as the resulting decoder computational cost when compared with the global model equivalent.

cs.NE↗

arXiv2021

Deep Learning with a Classifier System: Initial Results

This article presents the first results from using a learning classifier system capable of performing adaptive computation with deep neural networks. Individual classifiers within the population are composed of two neural networks. The first acts as a gating or guarding component, which enables the conditional computation of an associated deep neural network on a per instance basis. Self-adaptive mutation is applied upon reproduction and prediction networks are refined with stochastic gradient descent during lifetime learning. The use of fully-connected and convolutional layers are evaluated on handwritten digit recognition tasks where evolution adapts (i) the gradient descent learning rate applied to each layer (ii) the number of units within each layer, i.e., the number of fully-connected neurons and the number of convolutional kernel filters (iii) the connectivity of each layer, i.e., whether each weight is active (iv) the weight magnitudes, enabling escape from local optima. The system automatically reduces the number of weights and units while maintaining performance after achieving a maximum prediction error.

cs.NE↗

arXiv2021

Are Artificial Dendrites useful in NeuroEvolution?

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 neuroevolution. The phenomenon of separate dendrite activation thresholds on connections is allowed to emerge under an evolutionary process. It is shown how such processing can be positively selected for, particularly for connections between the hidden and output layer, and increases performance.

cs.NE↗

arXiv2021

On Sexual Selection

Sexual selection is a fundamental aspect of evolution for all eukaryotic organisms with mating types. This paper suggests intersexual selection is best viewed as a mechanism to compensate for the unavoidable dynamics of coevolution between sexes that emerge with isogamy. Using the NK model of fitness landscapes, the conditions under which allosomes emerge are first explored. This extends previous work on the evolution of sex where the fitness landscape smoothing of a rudimentary form of the Baldwin effect is suggested as the underlying cause. The NKCS model of coevolution is then used to show how varying fitness landscape size, ruggedness, and connectedness can vary the conditions under which a very simple sexual selection mechanism proves beneficial. This is found to be the case whether one or both sexes exploit sexual selection.

q-bio.PE↗

arXiv2020

Evolving Nano Particle Cancer Treatments with Multiple Particle Types

Evolutionary algorithms have long been used for optimization problems where the appropriate size of solutions is unclear a priori. The applicability of this methodology is here investigated on the problem of designing a nano-particle (NP) based drug delivery system targeting cancer tumours. Utilizing a treatment comprising of multiple types of NPs is expected to be more effective due to the higher complexity of the treatment. This paper begins by utilizing the well-known NK model to explore the effects of fitness landscape ruggedness upon the evolution of genome length and, hence, solution complexity. The size of a novel sequence and the absence or presence of sequence deletion are also considered. Results show that whilst landscape ruggedness can alter the dynamics of the process, it does not hinder the evolution of genome length. These findings are then explored within the aforementioned real-world problem. In the first known instance, treatments with multiple types of NPs are used simultaneously, via an agent-based open source physics-based cell simulator. The results suggest that utilizing multiple types of NPs is more efficient when the solution space is explored with the evolutionary techniques under a predefined computational budget.

cs.NE↗

arXiv2020

On the Baldwin Effect under Coevolution

The potentially beneficial interaction between learning and evolution, the Baldwin effect, has long been established. This paper considers their interaction within a coevolutionary scenario, ie, where the adaptations of one species typically affects the fitness of others. Using the NKCS model, which allows the systematic exploration of the effects of fitness landscape size, ruggedness, and degree of coupling, it is shown how the amount of learning and the relative rate of evolution can alter behaviour.

cs.NE↗

arXiv2020

Exploring Distributed Control with the NK Model

The NK model has been used widely to explore aspects of natural evolution and complex systems. This paper introduces a modified form of the NK model for exploring distributed control in complex systems such as organisations, social networks, collective robotics, etc. 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.

cs.NE↗

arXiv2020

Utilizing Differential Evolution into optimizing targeted cancer treatments

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. A basic DE algorithm, namely "DE/rand/1" was used to optimize the simulated design of a targeted drug delivery system for tumor treatment on PhysiCell simulator. The suggested approach proved to be more efficient than a standard genetic algorithm, which was not able to escape local minima after a predefined number of generations. The key attribute of DE that enables it to outperform standard EAs, is the fact that it keeps the diversity of the population high, throughout all the generations. This work will be incorporated with ongoing research in a more wide applicability platform that will design, develop and evaluate targeted drug delivery systems aiming cancer tumours.

cs.NE↗

arXiv2020

Novelty search employed into the development of cancer treatment simulations

Conventional optimization methodologies may be hindered when the automated search is stuck into local optima because of a deceptive objective function landscape. Consequently, open ended search methodologies, such as novelty search, have been proposed to tackle this issue. Overlooking the objective, while putting pressure into discovering novel solutions may lead to better solutions in practical problems. Novelty search was employed here to optimize the simulated design of a targeted drug delivery system for tumor treatment under the PhysiCell simulator. A hybrid objective equation was used containing both the actual objective of an effective tumour treatment and the novelty measure of the possible solutions. Different weights of the two components of the hybrid equation were investigated to unveil the significance of each one.

cs.NE↗

arXiv2020

The Evolution of Sex Chromosomes through the Baldwin Effect

It has recently been suggested that the fundamental haploid-diploid cycle of eukaryotic sex exploits a rudimentary form of the Baldwin effect. Thereafter the other associated phenomena can be explained as evolution tuning the amount and frequency of learning experienced by an organism. Using the well-known NK model of fitness landscapes it is here shown that the emergence of sex determination systems can also be explained under this view of eukaryotic evolution.

q-bio.PE↗

arXiv2019

Haploid-Diploid Evolution: Nature's Memetic Algorithm

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. A form of the Baldwin effect has been identified as inherent to the evolutionary mechanisms of eukaryotes and a simplified version is presented here which maintains such behaviour. Using a well-known abstract tuneable model, it is shown that varying fitness landscape ruggedness varies the benefit of haploid-diploid algorithms. Moreover, the methodology is applied to optimise the targeted delivery of a therapeutic compound utilizing nano-particles to cancerous tumour cells with the multicellular simulator PhysiCell.

cs.NE↗

arXiv2019

Autoencoding with a Learning Classifier System: Initial Results

Autoencoders enable data dimensionality reduction and a key component of many (deep) learning systems. This short paper introduces a form of Holland's Learning Classifier System (LCS) to perform autoencoding building upon a previously presented form of LCS that utilises unsupervised learning for clustering. Initial results using a neural network representation suggest it is an effective approach to reduction.

cs.NE↗