papers

Publications (6)

cs.LG2020

Learned Low Precision Graph Neural Networks

Yiren Zhao, Duo Wang, Daniel Bates +3

Deep Graph Neural Networks (GNNs) show promising performance on a range of graph tasks, yet at present are costly to run and lack many of the optimisations applied to DNNs. We show…

cs.AR2016

Configurable memory systems for embedded many-core processors

Daniel Bates, Alex Chadwick, Robert Mullins

The memory system of a modern embedded processor consumes a large fraction of total system energy. We explore a range of different configuration options and show that a reconfigura…

cs.AR2022

Muntjac -- Open Source Multicore RV64 Linux-capable SoC

Xuan Guo, Daniel Bates, Robert Mullins +1

Muntjac is an open-source collection of components which can be used to build a multicore, Linux-capable system-on-chip. This includes a 64-bit RISC-V core, a cache subsystem, and…

cs.LG2019

Focused Quantization for Sparse CNNs

Yiren Zhao, Xitong Gao, Daniel Bates +2

Deep convolutional neural networks (CNNs) are powerful tools for a wide range of vision tasks, but the enormous amount of memory and compute resources required by CNNs pose a chall…

cs.LG2022

Fast Neural Network based Solving of Partial Differential Equations

Jaroslaw Rzepecki, Daniel Bates, Chris Doran

We present a novel method for using Neural Networks (NNs) for finding solutions to a class of Partial Differential Equations (PDEs). Our method builds on recent advances in Neural…

cs.LG2021

Sponge Examples: Energy-Latency Attacks on Neural Networks

Ilia Shumailov, Yiren Zhao, Daniel Bates +3

The high energy costs of neural network training and inference led to the use of acceleration hardware such as GPUs and TPUs. While this enabled us to train large-scale neural netw…