Master of science Daniel Johansen Trosten will Wednesday August 23rd, 2023, at 12:15 hold his disputas for the PhD degree in Science. The title of his thesis is:
"Improving Representation Learning for Deep Clustering and Few-shot Learning"
The amounts of data in the world have increased dramatically in recent years, and it is quickly becoming infeasible for humans to label all these data. It is therefore crucial that modern machine learning systems can operate with few or no labels. The introduction of deep learning and deep neural networks has led to impressive advancements in several areas of machine learning. These advancements are largely due to the unprecedented ability of deep neural networks to learn powerful representations from a wide range of complex input signals. This ability is especially important when labeled data is limited, as the absence of a strong supervisory signal forces models to rely more on intrinsic properties of the data and its representations.
This thesis focuses on two key concepts in deep learning with few or no labels. First, we aim to improve representation quality in deep clustering - both for single-view and multi-view data. Current models for deep clustering face challenges related to properly representing semantic similarities, which is crucial for the models to discover meaningful clusterings. This is especially challenging with multi-view data, since the information required for successful clustering might be scattered across many views. Second, we focus on few-shot learning, and how geometrical properties of representations influence few-shot classification performance. We find that a large number of recent methods for few-shot learning embed representations on the hypersphere. Hence, we seek to understand what makes the hypersphere a particularly suitable embedding space for few-shot learning.
Evaluation Committee
Supervisors
The Disputas will be led by Professor John Sigurd Mjøen Svendsen, Pro-Dean at the Faculty of Science and Technology at UiT.
Streaming site
The disputas and trial lecture will be streamed from these sites:
Disputas (12:15 - 16:00)
Trial Lecture (10:15 - 11:15)
Thesis
The thesis is available through Munin.