Completely Automated CNN Architecture Design Based on Blocks

The performance of convolutional neural networks (CNNs) highly relies on their architectures. In order to design a CNN with promising performance, extensive expertise in both CNNs and the investigated problem domain is required, which is not necessarily available to every interested user. To address...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transaction on neural networks and learning systems Ročník 31; číslo 4; s. 1242 - 1254
Hlavní autoři: Sun, Yanan, Xue, Bing, Zhang, Mengjie, Yen, Gary G.
Médium: Journal Article
Jazyk:angličtina
Vydáno: United States IEEE 01.04.2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:
Algorithms
Artificial neural networks
Automatic architecture design
Classification
Competition
Computer applications
Computer architecture
convolutional neural networks (CNNs)
Domains
Encoding
Evolutionary computation
evolutionary deep learning
Genetic algorithms
genetic algorithms (GAs)
Neural networks
Optimization
Sociology
Statistics
User requirements
ISSN:2162-237X, 2162-2388, 2162-2388
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The performance of convolutional neural networks (CNNs) highly relies on their architectures. In order to design a CNN with promising performance, extensive expertise in both CNNs and the investigated problem domain is required, which is not necessarily available to every interested user. To address this problem, we propose to automatically evolve CNN architectures by using a genetic algorithm (GA) based on ResNet and DenseNet blocks. The proposed algorithm is completely automatic in designing CNN architectures. In particular, neither preprocessing before it starts nor postprocessing in terms of CNNs is needed. Furthermore, the proposed algorithm does not require users with domain knowledge on CNNs, the investigated problem, or even GAs. The proposed algorithm is evaluated on the CIFAR10 and CIFAR100 benchmark data sets against 18 state-of-the-art peer competitors. Experimental results show that the proposed algorithm outperforms the state-of-the-art CNNs hand-crafted and the CNNs designed by automatic peer competitors in terms of the classification performance and achieves a competitive classification accuracy against semiautomatic peer competitors. In addition, the proposed algorithm consumes much less computational resource than most peer competitors in finding the best CNN architectures.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
ISSN:2162-237X
2162-2388
2162-2388
DOI:10.1109/TNNLS.2019.2919608