Please use this identifier to cite or link to this item:
http://hdl.handle.net/20.500.11861/7410
Title: | Probabilistic grammar-based deep neuroevolution |
Authors: | Wong, Pak-Kan Wong, Man-Leung Prof. LEUNG Kwong Sak |
Issue Date: | Jul-2019 |
Source: | GECCO 2019 Companion - Proceedings of the 2019 Genetic and Evolutionary Computation Conference Companion, 2019, pp. 87-88 |
Conference: | GECCO 2019 Companion |
Abstract: | Designing deep neural networks by human engineers can be challenging because there are various choices of deep neural network structures. We developed a deep neuroevolution system to automatically design deep neural network structures using deep neuroevolution. Our approach defines a set of structures using a probabilistic grammar and searches for best network structures using Probabilistic Model Building Genetic Programming. Our approach takes advantage of the probabilistic dependencies found among the structures of networks. The system was applied to tackle the problem of the physiological signal classification of abnormal heart rhythm. In the classification problem, our discovered model is more accurate than AlexNet. Our discovered model uses about 2% of the total amount of parameters of AlexNet. |
Type: | Conference Paper |
URI: | http://hdl.handle.net/20.500.11861/7410 |
DOI: | 10.1145/3319619.3326778 |
Appears in Collections: | Applied Data Science - Publication |
Find@HKSYU Show full item record
SCOPUSTM
Citations
3
checked on Nov 17, 2024
Page view(s)
44
Last Week
1
1
Last month
checked on Nov 21, 2024
Google ScholarTM
Impact Indices
Altmetric
PlumX
Metrics
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.