Zobrazeno 1 - 10
of 785
pro vyhledávání: '"Robertson, Duncan A."'
Accurate, high-resolution 3D mapping of environmental terrain is critical in a range of disciplines. In this study, we develop a new technique, called the PCFilt-94 algorithm, to extract 3D point clouds from coarse resolution millimetre-wave radar da
Externí odkaz:
http://arxiv.org/abs/2310.08120
Autor:
Murugan, Jeff, Robertson, Duncan
Topological Data Analysis (TDA) is a novel, and relatively new approach to analysing high-dimensional data sets. It does this by focussing on global properties like the shape and connectivity of the data giving it a significant advantage over more co
Externí odkaz:
http://arxiv.org/abs/1904.11044
Autor:
Cole, Lorna J., Baddeley, John A., Robertson, Duncan, Topp, Cairistiona F.E., Walker, Robin L., Watson, Christine A.
Publikováno v:
In Agriculture, Ecosystems and Environment 1 January 2022 323
Autor:
Hadley, Liza *, Challenor, Peter, Dent, Chris, Isham, Valerie, Mollison, Denis, Robertson, Duncan A., Swallow, Ben, Webb, Cerian R.
Publikováno v:
In Epidemics December 2021 37
We propose a new method for creating computationally efficient and compact convolutional neural networks (CNNs) using a novel sparse connection structure that resembles a tree root. This allows a significant reduction in computational cost and number
Externí odkaz:
http://arxiv.org/abs/1605.06489
Deep Convolutional Neural Networks (CNNs) have recently evinced immense success for various image recognition tasks. However, a question of paramount importance is somewhat unanswered in deep learning research - is the selected CNN optimal for the da
Externí odkaz:
http://arxiv.org/abs/1604.06832
Autor:
Ioannou, Yani, Robertson, Duncan, Zikic, Darko, Kontschieder, Peter, Shotton, Jamie, Brown, Matthew, Criminisi, Antonio
This paper investigates the connections between two state of the art classifiers: decision forests (DFs, including decision jungles) and convolutional neural networks (CNNs). Decision forests are computationally efficient thanks to their conditional
Externí odkaz:
http://arxiv.org/abs/1603.01250
Publikováno v:
International Conference on Learning Representations (ICLR), San Juan, Puerto Rico, 2-4 May 2016
We propose a new method for creating computationally efficient convolutional neural networks (CNNs) by using low-rank representations of convolutional filters. Rather than approximating filters in previously-trained networks with more efficient versi
Externí odkaz:
http://arxiv.org/abs/1511.06744