Incorporating sequential and geometric structure into deep neural networks

Thesis

Modern deep learning models have achieved great success, but they struggle with structured inputs unless they ingest massive amounts of data, or are guided by inductive biases that reflect the data’s inherent sequential or geometric structure. This thesis focuses on improving model performance in settings like time series and graph-structured data, which are common in real-world domains such as finance or healthcare. In particular, it addresses key challenges in these domains, such as the pre...

Expand abstract

Authors: Arroyo Nunez, A

• DOI: 10.5287/ora-6gj8m88d9
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: graph representation learning; sequence modelling
• Subjects: Deep Learning