High performance deep learning on resource constrained platforms

Thesis

After a decade of accelerated progress in the different areas of machine learning (ML), it has become virtually impossible to not interact with ML-powered applications and services in our everyday lives. Recommender systems, computational photography, speech translation or, getting directions are only a handful of examples of what can be done from our smartphones or other smart devices, sometimes battery-powered, present in the places where we live, work and, socialize. However, despite th...

Expand abstract

Authors: Fernández-Marqués, J

• DOI: 10.5287/ora-7ryjdeebb
• Type of award: DPhil
• Level of award: Doctoral
• Awarding institution: University of Oxford
• Language: English
• Keywords: efficient machine learning; machine learning; quantization; hardware-aware machine learning; convolutional neural networks; winograd; graph neural networks; deep learning; machine learning systems
• Subjects: Deep learning (Machine learning)