Kyrillidis, Anastasios2023-09-012023-09-012023-082023-07-05August 202Wolfe, Cameron Ronald. "Theories and Perspectives on Practical Deep Learning." (2023) Diss., Rice University. https://hdl.handle.net/1911/115248.https://hdl.handle.net/1911/115248Deep neural networks (DNNs) have proven to be adept at accurately automating many tasks (e.g., image and text classification, object detection, text generation, and more). Across most domains, DNNs tend to achieve better performance with increasing scale, both in terms of dataset and model size. As such, the benefit of DNNs comes at a steep computational (and monetary) cost, which can limit their applicability. This document aims to identify novel and intuitive techniques that can make deep learning more usable across domains and communities.application/pdfengCopyright is held by the author, unless otherwise indicated. Permission to reuse, publish, or reproduce the work beyond the bounds of fair use or other exemptions to copyright law must be obtained from the copyright holder.neural networkspruningdistributed traininghyperparameter tuningonline learningstreaming learningThesis2023-09-01