Massey Documents by Type

Permanent URI for this communityhttps://mro.massey.ac.nz/handle/10179/294

Browse

Has files: YesSubject: search.filters.subject.Complexity

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Modeling the Chaotic Semantic States of Generative Artificial Intelligence (AI): A Quantum Mechanics Analogy Approach
    (Association for Computing Machinery, 2025-12-01) Liu T; McIntosh TR; Susnjak T; Watters P; Halgamuge MN
    Generative artificial intelligence (AI) models have revolutionized intelligent systems by enabling machines to produce human-like content across diverse domains. However, their outputs often exhibit unpredictability due to complex and opaque internal semantic states, posing challenges for reliability in real-world applications. In this paper, we introduce the AI Uncertainty Principle, a novel theoretical framework inspired by quantum mechanics, to model and quantify the inherent unpredictability in generative AI outputs. By drawing parallels with the uncertainty principle and superposition, we formalize the trade-off between the precision of internal semantic states and output variability. Through comprehensive experiments involving state-of-the-art models and a variety of prompt designs, we analyze how factors such as specificity, complexity, tone, and style influence model behavior. Our results demonstrate that carefully engineered prompts can significantly enhance output predictability and consistency, while excessive complexity or irrelevant information can increase uncertainty. We also show that ensemble techniques, such as Sigma-weighted aggregation across models and prompt variations, effectively improve reliability. Our findings have profound implications for the development of intelligent systems, emphasizing the critical role of prompt engineering and theoretical modeling in creating AI technologies that perceive, reason, and act predictably in the real world.
  • Thumbnail Image
    Item
    Multicomponent Metal-Organic Frameworks
    (Wiley-VCH GmbH, Weinheim, 2023-10-26) Lee SJ; Telfer SG
    Metal-organic frameworks (MOFs) are constructed from metal ions or clusters and organic linkers. Typical MOFs are rather simple, comprising just one type of joint and linker. An additional degree of structural complexity can be introduced by using multiple different components that are assembled into the same framework In the early days of MOF chemistry, conventional wisdom held that attempting to prepare frameworks starting from such a broad set of components would lead to multiple different phases. However, this review highlights how this view was mistaken and frameworks comprising multiple different components can be deliberately designed and synthesized. When coupled to structural order and periodicity, the presence of multiple components leads to exceptional functional properties that can be understood at the atomic level.
  • Thumbnail Image
    Item
    Grappling with complexity : finding the core problems behind aircraft accidents : a thesis presented in partial fulfilment of the requirements for the degree of Doctor of Philosophy in Aviation at Massey University, Palmerston North, New Zealand
    (Massey University, 2006) Zotov, Dmitri Victorovitch
    The purpose of accident investigation is the discovery of causal factors, so that they may be remedied, in order to avert the recurrence of accidents (ICAO, 1994). However, experience has shown that the present intuitive methods of analysis do not always achieve this aim. Investigation failure may come about because of failure to discover causal factors, or to devise effective remedies, or to persuade those in a position to act of the need to do so. Each of these types of failure can be made less likely by the use of formal analytical methods which can show whether information gathering has been incomplete, and point to the sources of additional information that may be needed. A formal analysis can be examined by formal logical tests. Also, the use of formal change mechanisms can not only devise changes likely to be effective, but can present these changes in such a way that the case for them is compelling. Formal methods currently available are concerned with what happened, and why it happened. To produce generic remedies which might avert future accidents of similar type, some formal change mechanism is needed. The Theory of Constraints has become widely adopted in business as a way of replacing undesirable effects with desired outcomes. The Theory of Constraints has not previously been used for safety investigation, and a principal object of this thesis is to see whether it can usefully be employed in this area. It is demonstrated that the use of formal methodology can bring to light factors which were overlooked during an official accident investigation, and can ‘tell the story’ in a more coherent manner than is possible with present methods. The recommendations derived from the formal analysis are shown to be generic in nature, rather than particular to the airline involved and the accident studied, and so could have a wider effect in improving safety.