Ivana Kajić, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Chris Eliasmith
Nabiha Asghar, PhD candidate
David R. Cheriton School of Computer Science
In human-computer interaction (HCI), one of the technological goals is to build human-like artificial agents that can think, decide and behave like humans during the interaction. A prime example is a dialogue system, where the agent should converse fluently and coherently with a user and connect with them emotionally. Humanness and emotion-awareness of interactive artificial agents have been shown to improve user experience and help attain application-specific goals more quickly. However, achieving human-likeness in HCI systems is contingent on addressing several philosophical and scientific challenges. In this thesis, I address two such challenges: replicating the human ability to 1) correctly perceive and adopt emotions, and 2) communicate effectively through language.
Priyank Jaini, PhD candidate
David R. Cheriton School of Computer Science
Multivariate density estimation is a central problem in unsupervised machine learning that has been studied immensely in both statistics and machine learning. Several methods have thus been proposed for density estimation including classical techniques like histograms, kernel density estimation methods, mixture models, and more recently neural density estimation that leverages the recent advances in deep learning and neural networks to tractably represent a density function. In today's age when large amounts of data are being generated in almost every field it is of paramount importance to develop density estimation methods that are cheap both computationally and in memory cost. The main contribution of this thesis is in providing a principled study of parametric density estimation methods using mixture models and triangular maps for neural density estimation.
Shrinu Kushagra, PhD candidate
David R. Cheriton School of Computer Science
Clustering aims to group together data instances which are similar while simultaneously separating the dissimilar instances. The task of clustering is challenging due to many factors. The most well-studied is the high computational cost. The clustering task can be viewed as an optimization problem where the goal is to minimize a certain cost function (like k-means cost or k-median cost). Not only are the minimization problems NP-Hard but often also NP-Hard to approximate (within a constant factor). There are two other major issues in clustering, namely under-specificity and noise-robustness.
Aaron Voelker, PhD candidate
David R. Cheriton School of Computer Science
Dynamical systems are universal computers. They can perceive stimuli, remember, learn from feedback, plan sequences of actions, and coordinate complex behavioural responses. The Neural Engineering Framework (NEF) provides a general recipe to formulate models of such systems as coupled sets of nonlinear differential equations and compile them onto recurrently connected spiking neural networks — akin to a programming language for spiking models of computation. The Nengo software ecosystem supports the NEF and compiles such models onto neuromorphic hardware.
Carolyn Lamb, PhD candidate
David R. Cheriton School of Computer Science
This thesis is driven by the question of how computers can generate poetry, and how that poetry can be evaluated. We survey existing work on computer-generated poetry and interdisciplinary work on how to evaluate this type of computer-generated creative product.
Nicole McNabb, Master’s candidate
David R. Cheriton School of Computer Science
Clustering is the task of partitioning data so that “similar” points are grouped together and “dissimilar” ones are separated. In general, this is an ill-defined task. One way to make clustering well-defined is to introduce a clustering objective to optimize. While many common objectives such as k-means are known to be NP-hard, heuristics output “nice” clustering solutions efficiently in practice. This work analyzes two avenues of theoretical research that attempt to explain this discrepancy.
Irish Medina, Master’s candidate
David R. Cheriton School of Computer Science
Smart water meters have been installed across Abbotsford, British Columbia, Canada, to measure the water consumption of households in the area. Using this water consumption data, we develop machine learning and deep learning models to predict daily water consumption for existing multi-family residences. We also present a new methodology for predicting the water consumption of new housing developments.
Daniel Recoskie, PhD candidate
David R. Cheriton School of Computer Science
The wavelet transform is a well-studied and understood analysis technique used in signal processing. In wavelet analysis, signals are represented by a sum of self-similar wavelet and scaling functions. Typically, the wavelet transform makes use of a fixed set of wavelet functions that are analytically derived. We propose a method for learning wavelet functions directly from data. We impose an orthogonality constraint on the functions so that the learned wavelets can be used to perform both analysis and synthesis. We accomplish this by using gradient descent and leveraging existing automatic differentiation frameworks. Our learned wavelets are able to capture the structure of the data by exploiting sparsity. We show that the learned wavelets have similar structure to traditional wavelets.
Vineet John, Master’s candidate
David R. Cheriton School of Computer Science
This thesis tackles the problem of disentangling the latent style and content variables in a language modelling context. This involves splitting the latent representations of documents by learning which features of a document are discriminative of its style and content, and encoding these features separately using neural network models.