arXiv subjects

Michael O'Neill

Publications and source records attributed to Michael O'Neill.

At least 19 recordsLinked to original sources

arXiv2026

Breaking the Central Bias: Spatially Partitioned Experts for Coordinate-Based Neuroevolution

Evolvable-Substrate HyperNEAT (ES-HyperNEAT), a bio-inspired indirect encoding that determines neuron placement and connection weights from spatial coordinates, exhibits a failure mode on MNIST as a diagnostic benchmark. Because input pixels map to a coordinate space centered at the origin, evolved networks converge on a small central cluster of input pixels, a spatial-concentration bias; prior work observed only 21% mean accuracy in this regime. Is this bias an optimization artifact or an architectural ceiling? Inspired by Mixture-of-Experts (MoE) principles, we partition the input into non-overlapping spatial segments, each assigned to a separately evolved specialist network. With 13 such experts, this design reaches 43% mean accuracy, a 106% relative improvement over the baseline. The architectural gain does not depend on data-driven aggregation: equal-weighted averaging, which uses no validation data, already yields a 70% improvement; the gain comes from partitioning, not the weighting. Receptive-field analysis shows the mechanism: partitioning forces evolution to discover features across the entire image, expanding active pixel coverage from 4% to 79%. Absolute accuracy stays below gradient-trained baselines, but the relative gain points to central bias, not the evolutionary search. Two tools are designed to generalize beyond MNIST: a receptive-field diagnostic for silent input-coverage collapse, and a spatial-partitioning remedy that restores coverage.

cs.NE↗

arXiv2026

Investigating Hyperparameter Optimization and Transferability for ES-HyperNEAT: A TPE Approach

Neuroevolution of Augmenting Topologies (NEAT) and its advanced version, Evolvable-Substrate HyperNEAT (ES-HyperNEAT), have shown great potential in developing neural networks. However, their effectiveness heavily depends on the selection of hyperparameters. This study investigates the optimization of ES-HyperNEAT hyperparameters using the Tree-structured Parzen Estimator (TPE) on the MNIST classification task, exploring a search space of over 3 billion potential combinations. TPE effectively navigates this vast space, significantly outperforming random search in terms of mean, median, and best accuracy. During the validation process, the best hyperparameter configuration found by TPE achieves an accuracy of 29.00% on MNIST, surpassing previous studies while using a smaller population size and fewer generations. The transferability of the optimized hyperparameters is explored in logic operations and Fashion-MNIST tasks, revealing successful transfer to the more complex Fashion-MNIST problem but limited to simpler logic operations. This study emphasizes a method to unlock the full potential of neuroevolutionary algorithms and provides insights into the hyperparameters' transferability across tasks of varying complexity.

cs.NE↗

arXiv2026

Tensor-Accelerated Eager Multi-Resolution Grids for Evolving Large-Scale Substrates

In neuroevolution, indirect encoding generates neural network connectivity from a compact genome rather than specifying each connection. ES-HyperNEAT automatically discovers where to place hidden nodes by examining CPPN output patterns: it recursively subdivides space using a quadtree, expanding regions where CPPN outputs show high variance. This adaptive approach discovers network topology without manual substrate specification, extending the fixed-grid HyperNEAT framework built on NEAT. However, the quadtree resists tensorization. Each depth level depends on the parent's variance, forcing sequential evaluation. Different CPPNs produce different subdivision patterns, preventing batching. And variable leaf counts are incompatible with JAX's static shape requirement for JIT compilation. Our prior work confirmed these limits at depths exceeding 5, and a JAX reimplementation of the quadtree yielded only marginal speedup despite batched optimizations, motivating the eager reformulation presented here. We present EMR-HyperNEAT, which evaluates all positions at all resolutions up front, then filters using the same variance criterion: ES-HyperNEAT's subdivide_if(var > $\theta$) becomes eval_all(); filter(var > $\theta$). This performs more CPPN queries than necessary, but all queries become independent and parallelizable across both cores and population members, reducing complexity from \BigO($4^D$) to \BigO($4^D/P$) across $P$ parallel cores. Recurrent substrate configurations become feasible through a connection type taxonomy. The experiments section validates 12-34$\times$ on-device GPU speedup on XOR at depths 5-7, and empirically higher solve rates across benchmarks.

cs.NE↗

arXiv2026

On Scaling Coordinate-Based Neuroevolution: The Quadtree Bottleneck in ES-HyperNEAT

ES-HyperNEAT evolves substrate topology through adaptive quadtree subdivision; to our knowledge, no implementation with full population-level GPU parallelization exists. We present JAX-ESHN, a JAX-based implementation targeting GPU parallelization with batched CPPN queries, and benchmark it against the CPU-based PUREPLES Baseline across five tasks: XOR, Parity-3, circle classification, sine regression, and CartPole. The core limitation is structural: each CPPN discovers a unique set of substrate positions, preventing population-level vectorization via vmap. On XOR, the CPU Baseline's runtime scales exponentially with depth while JAX-ESHN's construction cost on GPU (compilation plus first-generation evaluation) plateaus at deep substrates, so JAX-ESHN solves reliably where the Baseline rarely succeeds, with lower runtime variance. A CPU-vs-CPU multi-benchmark control reproduces the same scaling divergence across Boolean, continuous, and control task types, confirming it is a property of the substrate-discovery implementation, not of GPU hardware. An alternative data structure (Hierarchical Spatial Hash Grid) fails not because it precomputes positions but because it applies the variance test independently per position, discarding the quadtree's parent-gated filtering and with it the adaptive sparsity essential to ES-HyperNEAT. These findings define the structural constraints any substrate-discovery method must satisfy to scale coordinate-based neuroevolution; the companion EMR-HyperNEAT reformulation, which replaces adaptive subdivision with eager evaluation of a static multi-resolution grid, satisfies them and resolves the bottleneck this paper characterizes.

cs.NE↗

arXiv2025

GeoWarp: Warped spatial processes for inferring subsea sediment properties

For offshore structures like wind turbines, subsea infrastructure, pipelines, and cables, it is crucial to quantify the properties of the seabed sediments at a proposed site. However, data collection offshore is costly, so analysis of the seabed sediments must be made from measurements that are spatially sparse. Adding to this challenge, the structure of the seabed sediments exhibits both nonstationarity and anisotropy. To address these issues, we propose GeoWarp, a hierarchical spatial statistical modeling framework for inferring the 3-D geotechnical properties of subsea sediments. GeoWarp decomposes the seabed properties into a region-wide vertical mean profile (modeled using B-splines), and a nonstationary 3-D spatial Gaussian process. Process nonstationarity and anisotropy are accommodated by warping space in three dimensions and by allowing the process variance to change with depth. We apply GeoWarp to measurements of the seabed made using cone penetrometer tests (CPTs) at six sites on the North West Shelf of Australia. We show that GeoWarp captures the complex spatial distribution of the sediment properties, and produces realistic 3-D simulations suitable for downstream engineering analyses. Through cross-validation, we show that GeoWarp has predictive performance superior to other state-of-the-art methods, demonstrating its value as a tool in offshore geotechnical engineering.

stat.AP↗

arXiv2023

Amplifying Limitations, Harms and Risks of Large Language Models

We present this article as a small gesture in an attempt to counter what appears to be exponentially growing hype around Artificial Intelligence (AI) and its capabilities, and the distraction provided by the associated talk of science-fiction scenarios that might arise if AI should become sentient and super-intelligent. It may also help those outside of the field to become more informed about some of the limitations of AI technology. In the current context of popular discourse AI defaults to mean foundation and large language models (LLMs) such as those used to create ChatGPT. This in itself is a misrepresentation of the diversity, depth and volume of research, researchers, and technology that truly represents the field of AI. AI being a field of research that has existed in software artefacts since at least the 1950's. We set out to highlight a number of limitations of LLMs, and in so doing highlight that harms have already arisen and will continue to arise due to these limitations. Along the way we also highlight some of the associated risks for individuals and organisations in using this technology.

cs.CL↗

arXiv2023

Large Language Models in Sport Science & Medicine: Opportunities, Risks and Considerations

This paper explores the potential opportunities, risks, and challenges associated with the use of large language models (LLMs) in sports science and medicine. LLMs are large neural networks with transformer style architectures trained on vast amounts of textual data, and typically refined with human feedback. LLMs can perform a large range of natural language processing tasks. In sports science and medicine, LLMs have the potential to support and augment the knowledge of sports medicine practitioners, make recommendations for personalised training programs, and potentially distribute high-quality information to practitioners in developing countries. However, there are also potential risks associated with the use and development of LLMs, including biases in the dataset used to create the model, the risk of exposing confidential data, the risk of generating harmful output, and the need to align these models with human preferences through feedback. Further research is needed to fully understand the potential applications of LLMs in sports science and medicine and to ensure that their use is ethical and beneficial to athletes, clients, patients, practitioners, and the general public.

cs.CL↗

arXiv2021

An exploration of asocial and social learning in the evolution of variable-length structures

We wish to explore the contribution that asocial and social learning might play as a mechanism for self-adaptation in the search for variable-length structures by an evolutionary algorithm. An extremely challenging, yet simple to understand problem landscape is adopted where the probability of randomly finding a solution is approximately one in a trillion. A number of learning mechanisms operating on variable-length structures are implemented and their performance analysed. The social learning setup, which combines forms of both social and asocial learning in combination with evolution is found to be most performant, while the setups exclusively adopting evolution are incapable of finding solutions.

cs.NE↗

arXiv2020

Optimizing the Parameters of A Physical Exercise Dose-Response Model: An Algorithmic Comparison

The purpose of this research was to compare the robustness and performance of a local and global optimization algorithm when given the task of fitting the parameters of a common non-linear dose-response model utilized in the field of exercise physiology. Traditionally the parameters of dose-response models have been fit using a non-linear least-squares procedure in combination with local optimization algorithms. However, these algorithms have demonstrated limitations in their ability to converge on a globally optimal solution. This research purposes the use of an evolutionary computation based algorithm as an alternative method to fit a nonlinear dose-response model. The results of our comparison over 1000 experimental runs demonstrate the superior performance of the evolutionary computation based algorithm to consistently achieve a stronger model fit and holdout performance in comparison to the local search algorithm. This initial research would suggest that global evolutionary computation based optimization algorithms may present a fast and robust alternative to local algorithms when fitting the parameters of non-linear dose-response models.

cs.NE↗

arXiv2020

A Line-Search Descent Algorithm for Strict Saddle Functions with Complexity Guarantees

We describe a line-search algorithm which achieves the best-known worst-case complexity results for problems with a certain "strict saddle" property that has been observed to hold in low-rank matrix optimization problems. Our algorithm is adaptive, in the sense that it makes use of backtracking line searches and does not require prior knowledge of the parameters that define the strict saddle property.

math.OC↗

arXiv2019

A Log-Barrier Newton-CG Method for Bound Constrained Optimization with Complexity Guarantees

We describe an algorithm based on a logarithmic barrier function, Newton's method, and linear conjugate gradients that obtains an approximate minimizer of a smooth function over the nonnegative orthant. We develop a bound on the complexity of the approach, stated in terms of the required accuracy and the cost of a single gradient evaluation of the objective function and/or a matrix-vector multiplication involving the Hessian of the objective. The approach can be implemented without explicit calculation or storage of the Hessian.

math.OC↗

arXiv2019

High-Resolution Mammogram Synthesis using Progressive Generative Adversarial Networks

The ability to generate synthetic medical images is useful for data augmentation, domain transfer, and out-of-distribution detection. However, generating realistic, high-resolution medical images is challenging, particularly for Full Field Digital Mammograms (FFDM), due to the textural heterogeneity, fine structural details and specific tissue properties. In this paper, we explore the use of progressively trained generative adversarial networks (GANs) to synthesize mammograms, overcoming the underlying instabilities when training such adversarial models. This work is the first to show that generation of realistic synthetic medical images is feasible at up to 1280x1024 pixels, the highest resolution achieved for medical image synthesis, enabling visualizations within standard mammographic hanging protocols. We hope this work can serve as a useful guide and facilitate further research on GANs in the medical imaging domain.

cs.CV↗

arXiv2018

A Newton-CG Algorithm with Complexity Guarantees for Smooth Unconstrained Optimization

We consider minimization of a smooth nonconvex objective function using an iterative algorithm based on Newton's method and the linear conjugate gradient algorithm, with explicit detection and use of negative curvature directions for the Hessian of the objective function. The algorithm tracks Newton-conjugate gradient procedures developed in the 1980s closely, but includes enhancements that allow worst-case complexity results to be proved for convergence to points that satisfy approximate first-order and second-order optimality conditions. The complexity results match the best known results in the literature for second-order methods.

math.OC↗

arXiv2018

Behavior of Accelerated Gradient Methods Near Critical Points of Nonconvex Functions

We examine the behavior of accelerated gradient methods in smooth nonconvex unconstrained optimization, focusing in particular on their behavior near strict saddle points. Accelerated methods are iterative methods that typically step along a direction that is a linear combination of the previous step and the gradient of the function evaluated at a point at or near the current iterate. (The previous step encodes gradient information from earlier stages in the iterative process.) We show by means of the stable manifold theorem that the heavy-ball method method is unlikely to converge to strict saddle points, which are points at which the gradient of the objective is zero but the Hessian has at least one negative eigenvalue. We then examine the behavior of the heavy-ball method and other accelerated gradient methods in the vicinity of a strict saddle point of a nonconvex quadratic function, showing that both methods can diverge from this point more rapidly than the steepest-descent method.

math.OC↗

arXiv2018

Investigating the Evolvability of Web Page Load Time

Client-side Javascript execution environments (browsers) allow anonymous functions and event-based programming concepts such as callbacks. We investigate whether a mutate-and-test approach can be used to optimise web page load time in these environments. First, we characterise a web page load issue in a benchmark web page and derive performance metrics from page load event traces. We parse Javascript source code to an AST and make changes to method calls which appear in a web page load event trace. We present an operator based solely on code deletion and evaluate an existing "community-contributed" performance optimising code transform. By exploring Javascript code changes and exploiting combinations of non-destructive changes, we can optimise page load time by 41% in our benchmark web page.

cs.SE↗

arXiv2017

PonyGE2: Grammatical Evolution in Python

Grammatical Evolution (GE) is a population-based evolutionary algorithm, where a formal grammar is used in the genotype to phenotype mapping process. PonyGE2 is an open source implementation of GE in Python, developed at UCD's Natural Computing Research and Applications group. It is intended as an advertisement and a starting-point for those new to GE, a reference for students and researchers, a rapid-prototyping medium for our own experiments, and a Python workout. As well as providing the characteristic genotype to phenotype mapping of GE, a search algorithm engine is also provided. A number of sample problems and tutorials on how to use and adapt PonyGE2 have been developed.

cs.NE↗

arXiv2017

A Search for Improved Performance in Regular Expressions

The primary aim of automated performance improvement is to reduce the running time of programs while maintaining (or improving on) functionality. In this paper, Genetic Programming is used to find performance improvements in regular expressions for an array of target programs, representing the first application of automated software improvement for run-time performance in the Regular Expression language. This particular problem is interesting as there may be many possible alternative regular expressions which perform the same task while exhibiting subtle differences in performance. A benchmark suite of candidate regular expressions is proposed for improvement. We show that the application of Genetic Programming techniques can result in performance improvements in all cases. As we start evolution from a known good regular expression, diversity is critical in escaping the local optima of the seed expression. In order to understand diversity during evolution we compare an initial population consisting of only seed programs with a population initialised using a combination of a single seed individual with individuals generated using PI Grow and Ramped-half-and-half initialisation mechanisms.

cs.NE↗

arXiv2017

An efficient Search Tool for an Anti-Money Laundering Application of an Multi-national Bank's Dataset

Today, money laundering (ML) poses a serious threat not only to financial institutions but also to the nations. This criminal activity is becoming more and more sophisticated and seems to have moved from the clichy of drug trafficking to financing terrorism and surely not forgetting personal gain. Most of the financial institutions internationally have been implementing anti-money laundering solutions (AML) to fight investment fraud activities. In AML, the customer identification is an important task which helps AML experts to monitor customer habits: some being customer domicile, transactions that they are involved in etc. However, simple query tools provided by current DBMS as well as naive approaches in customer searching may produce incorrect and ambiguous results and their processing time is also very high due to the complexity of the database system architecture. In this paper, we present a new approach for identifying customers registered in an investment bank. This approach is developed as a tool that allows AML experts to quickly identify customers who are managed independently across separate databases. It is tested on real-world datasets, which are real and large financial datasets. Some preliminary experimental results show that this new approach is efficient and effective.

cs.DB↗