AbstractThe ability to perform a data-driven decision-making approach is at the core of Data Science, AI, and general Machine Learning techniques. To achieve a detailed data-driven approach, all possible scenarios must be considered, and their outcomes must be assessed logically and systematically to obtain accurate and applicable methods for knowledge discovery. These are considered in order to identify the best possible choice. Although, the data-driven approaches have been shown to be effective in theory, a major drawback is that it is typically associated with high computational complexity. Moreover, it is non-trivial to develop and train models with deep and complex model structures with potentially large number of parameters. However, there are compelling evidence from the cognitive sciences that intuition plays an important role in intelligence extraction and the associated decision-making process. More specifically, intuition can be used to identify, combine and discover knowledge in a 'parallel' manner and so more efficiently. As a consequence, the embedding of Artificial Intuition within Data Science is likely to provide novel ways to identify and process information.
The first contribution of this thesis is the introduction of a rigorous mathematical formulations and a novel algorithm for artificial intuition. Specifically, a mathematical formulation is introduced to describe a model that utilises semantic network to improve decision making. Moreover, the model that is introduced included some lemmas and propositions that provides a way of combining the aggregation of edges in semantic networks. The model implements techniques from computational linguistic via the processing pipeline to derive semantic networks. Moreover, the thesis contributed a state-of-the-art review of artificial intuition. The author provided relevant and detailed research about the concepts of artificial intuition as it relates to creativity, gut-feeling, rational thinking. It finally identified the umbrella concept called artificial intuition and identified some key requirements for the development of a model.
|Date of Award||16 Apr 2021|
|Supervisor||MARCELLO TROVATI (Director of Studies), SWAGAT KUMAR (Supervisor) & HARI MOHAN PANDEY (Supervisor)|
- Artificial Intuition, Artificial Intelligence
- Modelling, Network Theory
- Data Science, Decision Algorithms