3 papers
cs.PF2021
Multi-objective Evolutionary Approach for Efficient Kernel Size and Shape for CNN
Ziwei Wang, Martin A. Trefzer, Simon J. Bale +1
While state-of-the-art development in CNN topology, such as VGGNet and ResNet, have become increasingly accurate, these networks are computationally expensive involving billions of…
cs.OH2021
Multi-objective Digital Design Optimisation via Improved Drive Granularity Standard Cells
Linan Cao, Simon J. Bale, Martin A. Trefzer
To tackle the complexity of state-of-the-art electronic systems, silicon foundries continuously shrink the technology nodes and electronic design automation (EDA) vendors offer hie…
cs.ET2018
A Substrate-Independent Framework to Characterise Reservoir Computers
Matthew Dale, Julian F. Miller, Susan Stepney +1
The Reservoir Computing (RC) framework states that any non-linear, input-driven dynamical system (the reservoir) exhibiting properties such as a fading memory and input separabilit…