PhD Thesis: Examining Data Representations to Expand the Theory of Learning Metrics

Summary for Lay Audience: When developing an artificial intelligence (AI) protocol, selecting data representations is an important process. The representations we choose for our data are often influenced by the properties we gather from the data. It is equally true that selecting a data representation will guide our understanding of the data itself. Neural networks, some of our most prominent tools, are often considered a ‘black box’ from certain scientific vantages. Similarly, with regards to image domains, studies in the field of domain generalization have noted unexplained asymmetries. Through an investigation of these two categories with the tools of data representation, this research aims to expand the theoretical foundation of novel metrics for evaluating AI models and understanding the data on which they are trained.

Thesis available from Western Libraries

MSc Thesis: Machine Learning State Evaluation in Prismata

Abstract: Strategy games are a unique and interesting testbed for AI protocols due their complex rules and large state and action spaces. Recent work in game AI has shown that strong, robust AI agents can be created by combining existing techniques of deep learning and heuristic search. Heuristic search techniques typically make use of an evaluation function to judge the value of a game state, however these functions have historically been hand-coded by game experts. Recent results have shown that it is possible to use modern deep learning techniques to learn these evaluation functions, bypassing the need for expert knowledge.

In this thesis, we explore the implementation of this idea in Prismata, an online strategy game by Lunarch Studios. By generating game trace training data with existing state-of-the-art AI agents, we are able to use a Machine Learning (ML) approach to learn a new evaluation function. We trained several evaluation models with various parameters in order to compare prediction time with prediction accuracy. To evaluate the strength of our learned model, we ran a tournament between AI players which differ only in their state evaluation strategy. The results of this tournament demonstrate that our learned model when combined with the existing Prismata Hierarchical Portfolio Search system, produces a new AI agent which is able to defeat the previously strongest agents. A subset of the research presented in this thesis was the subject of a publication in the Artificial Intelligence and Interactive Digital Entertainment (AIIDE) 2019 Strategy Games Workshop [1].

Thesis available from Memorial University Libraries

A Hierarchical Approach to Examining Model Performance in Image Domains

  • In progress exploration of how hierarchical representations of images can explain model performance by revealing underlying properties of the image data.

  • Research based on collaborative work included in PhD thesis.

  • Author list revealed upon publication.

League of Legends Match Prediction

Categories determined using Euclidean Distance, see document

See poster

Title: On the Space of Coefficients of a Feedforward Neural Network

  • Dinesh Valluri, Rory Campbell

  • 2023 International Joint Conference on Neural Networks (IJCNN)

  • Poster presented at IJCNN 2023 by Rory Campbell

  • Link to publication: https://ieeexplore.ieee.org/abstract/document/10191403