Malcolm Heywood - Academia.edu (original) (raw)

Uploads

Papers by Malcolm Heywood

Lecture notes in computer science, 2024

Genetic Programming and Evolvable Machines, Nov 21, 2023

IGI Global eBooks, May 24, 2011

Internet trading is an irresistible business activity, which nevertheless is constrained by unres... more Internet trading is an irresistible business activity, which nevertheless is constrained by unresolved security issues. With e-tailers like amazon.com having a storefront for auction and the two largest traditional auction houses in the world, Christie’s and Sotheby’s, operating online auctions too; online auction systems are now playing an increasingly important role in e-commerce. However, online auction fraud has been reported in several high profile cases; this chapter offers some solutions for problems identified in online auction trading; which is largely unregulated and in which small auction sites have very little security. A secure architecture for online auction systems will greatly reduce the problems. The discussion herein is restricted to those factors that are deemed critical for ensuring that consumers gain the confidence required to participate in online auctions, and hence a broader spectrum of businesses are able to invest in integrating online auction systems into their commercial operations.

This work details and compares the application of configurable and reconfigurable computing techn... more This work details and compares the application of configurable and reconfigurable computing techniques to the estimation of binary 3×3 masks of 4-, 6- and 8-connectivity and logical operations of AND, OR and NOT. Specifically it is shown that the promise of reconfigurable as opposed to configurable computing provides a very efficient implementation of the morphological operator kernel

Lecture Notes in Computer Science, 2019

Visual reinforcement learning implies that, decision making policies are identified under delayed... more Visual reinforcement learning implies that, decision making policies are identified under delayed rewards from an environment. Moreover, state information takes the form of high-dimensional data, such as video. In addition, although the video might characterize a 3D world in high resolution, partial observability will place significant limits on what the agent can actually perceive of the world. This means that the agent also has to: (1) provide efficient encodings of state, (2) store the encodings of state efficiently in some form of memory, (3) recall such memories after arbitrary delays for decision making. In this work, we demonstrate how an external memory model facilitates decision making in the complex world of multi-agent ‘deathmatches’ in the ViZDoom first person shooter environment. The ViZDoom environment provides a complex environment of multiple rooms and resources in which agents are spawned from multiple different locations. A unique approach is adopted to defining external memory for genetic programming agents in which: (1) the state of memory is shared across all programs. (2) Writing is formulated as a probabilistic process, resulting in different regions of memory having short- versus long-term memory. (3) Read operations are indexed, enabling programs to identify regions of external memory with specific temporal properties. We demonstrate that agents purposefully navigate the world when external memory is provided, whereas those without external memory are limited to merely ‘flight or fight’ behaviour.

Proceedings of the Genetic and Evolutionary Computation Conference, Jul 13, 2019

The capacity of genetic programming (GP) to evolve a 'hero' character in the Dota 2 video... more The capacity of genetic programming (GP) to evolve a 'hero' character in the Dota 2 video game is investigated. A reinforcement learning context is assumed in which the only input is a 320-dimensional state vector and performance is expressed in terms of kills and net worth. Minimal assumptions are made to initialize the GP game playing agents - evolution from a tabula rasa starting point - implying that: 1) the instruction set is not task specific; 2) end of game performance feedback reflects quantitive properties a player experiences; 3) no attempt is made to impart game specific knowledge into GP, such as heuristics for improving navigation, minimizing partial observability, improving team work or prioritizing the protection of specific strategically important structures. In short, GP has to actively develop its own strategies for all aspects of the game. We are able to demonstrate competitive play with the built in game opponents assuming 1-on-1 competitions using the 'Shadow Fiend' hero. The single most important contributing factor to this result is the provision of external memory to GP. Without this, the resulting Dota 2 bots are not able to identify strategies that match those of the built-in game bot.

IFAC Proceedings Volumes, Aug 1, 1997

This paper describes the development of a computerised downtime recording system for an automotiv... more This paper describes the development of a computerised downtime recording system for an automotive assembly plant. It introduces the nature of the recording system environment at a large commercial van assembly plant and describes the system developed in terms of, characteristics and usability. The application analysis focuses on the user-computer interface.

Information Processing and Management, Jul 1, 2000

ABSTRACT

The goal of the CIFAR-10 benchmark is recast from the perspective of discovering light-weight as ... more The goal of the CIFAR-10 benchmark is recast from the perspective of discovering light-weight as well as accurate solutions. Specifically, the image data, on which CIFAR-10 is based, requires multiple practical issues to be addressed that are not often considered collectively when applying genetic programming to classification problems. Issues of particular interest include cardinality, multi-class classification and diversity maintenance. We demonstrate that diversity maintenance and cardinality can be approached simultaneously by adopting a data subset to compose pools of exemplars for lexicase selection. The issues of multi-class classification and solution simplicity are addressed by adopting the tangled program graph (TPG) approach to emergent modularity. In addition, the mutation operator is modified to ensure that class labels do not ‘die out’ during evolution. The resulting benchmarking study demonstrates solutions that are significantly more accurate than AutoML while providing comparable accuracies with solutions from unsupervised feature discovery, i.e. 70% accuracy. However, unlike the latter TPG solutions are several orders of magnitude simpler.

Lecture Notes in Computer Science, 2023

arXiv (Cornell University), Nov 28, 2022

2019 IEEE Symposium Series on Computational Intelligence (SSCI)

Different variations in deployment environments of machine learning techniques may affect the per... more Different variations in deployment environments of machine learning techniques may affect the performance of the implemented systems. The variations may cause changes in the data for machine learning solutions, such as in the number of classes and the extracted features. This paper investigates the capabilities of Genetic Programming (GP) for malicious insider detection in corporate environments under such changes. Assuming a Linear GP detector, techniques are introduced to allow a previously trained GP population to adapt to different changes in the data. The experiments and evaluation results show promising insider threat detection performances of the techniques in comparison with training machine learning classifiers from scratch. This reduces the amount of data needed and computation requirements for obtaining dependable insider threat detectors under new conditions.

Proceedings of the Genetic and Evolutionary Computation Conference, 2021

Tangled program graphs (TPG) support emergent modularity by first identifying subsets of programs... more Tangled program graphs (TPG) support emergent modularity by first identifying subsets of programs that can usefully coexist (a team/ graph node) and then identifying the circumstance under which to reference other teams (arc adaptation). Variation operators manipulate the content of teams and arcs. This introduces cycles into the TPG structures. Previously, this effect was eradicated at run time by marking nodes while evaluating TPG individuals. In this work, a new marking heuristic is introduced, that of arc (learner) marking. This means that nodes can be revisited, but not the same arcs. We investigate the impact of this through 18 titles from the Arcade Learning Environment. The performance and complexity of the policies appear to be similar, but with specific tasks (game titles) resulting in preferences for one scheme over another.

Proceedings of the Genetic and Evolutionary Computation Conference Companion, 2019

In real world applications, variation in deployment environments, such as changes in data collect... more In real world applications, variation in deployment environments, such as changes in data collection techniques, can affect the effectiveness and/or efficiency of machine learning (ML) systems. In this work, we investigate techniques to allow a previously trained population of Linear Genetic Programming (LGP) insider threat detectors to adapt to an expanded feature space. Experiments show that appropriate methods can be adopted to enable LGP to incorporate the new data efficiently, hence reducing computation requirements and expediting deployment under the new conditions.