Convolutional Neural Networks (CNN) are becoming a common presence in many
applications and services, due to their superior recognition accuracy. They are increasingly …

Deep Neural Networks (DNNs) are very computationally demanding, which presents a
significant barrier to their deployment, especially on resource-constrained devices …

Deep Neural Networks (DNNs) are extremely computationally demanding, which presents a
large barrier to their deployment on resource-constrained devices. Since such devices are …

This paper compares the latency, accuracy, training time and hardware costs of neural
networks compressed with our new multi-objective evolutionary algorithm called NEMOKD …

Improving the performance of deep neural networks (DNNs) is important to both the compiler
and neural architecture search (NAS) communities. Compilers apply program …

Optimizing the deployment of Deep Neural Networks (DNNs) is hard. Despite deep learning
approaches increasingly providing state-of-the-art solutions to a variety of difficult problems …

The use of BERT-based Natural Language Processing models has rapidly grown in recent
years, yet they remain difficult to deploy on edge devices where memory and compute …

This report details the design, implementation, and evaulation of “Orpheus”, a tool to
benchmark the inference of deep learning systems on heterogeneous devices, and enable …

GPUs critically rely on a complex system software stack comprising kernel-and user-space
drivers and JIT compilers. Yet, existing GPU simulators typically abstract away details of the …

Finding the Right Teacher for a Difficult Student Page 1 Finding the Right Teacher for a
Difficult Student Daniel Whettam The University of Edinburgh / The University of Bristol March …