Browse by author
Lookup NU author(s): Dr Robert Geada, David TowersORCiD, Dr Matthew ForshawORCiD, Dr Amir Atapour AbarghoueiORCiD, Dr Stephen McGough
This work is licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0).
The boundless possibility of neural networks which can be used to solve a problem - each with different performance - leads to a situation where a Deep Learning expert is required to identify the best neural network. This goes against the hope of removing the need for experts. Neural Architecture Search (NAS) offers a solution to this by automatically identifying the best architecture. However to date NAS work has focused on a small set of datasets which we argue are not representative of real-world problems. We introduce eight new datasets created for a series of NAS Challenges: AddNIST Language MultNIST CIFARTile Gutenberg Isabella GeoClassing and Chesseract. These datasets and challenges are developed to direct attention to issues in NAS development and to encourage authors to consider how their models will perform on datasets unknown to them at development time. We present experimentation using standard Deep Learning methods as well as the best results from challenge participants
Author(s): Geada R, Towers D, Forshaw M, Atapour-Abarghouei A, McGough AS
Publication type: Conference Proceedings (inc. Abstract)
Publication status: Published
Conference Name: 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Year of Conference: 2024
Pages: 22541-22550
Online publication date: 16/06/2024
Acceptance date: 02/04/2018
Date deposited: 04/11/2024
ISSN: 2575-7075
Publisher: IEEE
URL: https://doi.org/10.1109/CVPR52733.2024.02127
DOI: 10.1109/CVPR52733.2024.02127
Data Access Statement: These datasets have been created under the licence agreements of the original data. Where available, we have made the datasets publicly accessible under an CC BY 4.0 Licence. The Isabella dataset uses data from the Isabella Stewart Gardner Museum, which withholds the right to share modifications to the music they have made available. Instead of providing the dataset, we provide a Python script to convert music files obtained from the Museum3 into the format of the competition dataset on our GitHub 4.
Library holdings: Search Newcastle University Library for this item
ISBN: 9798350353006
