English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Convolutional neural networks (CNNs) are effective at solving difficultproblems like visual recognition, speech recognition and natural languageprocessing. However, performance gain comes at the cost of laborioustrial-and-error in designing deeper CNN architectures. In this paper, a geneticprogramming (GP) framework for convolutional neural network architecturesearch, abbreviated as GP-CNAS, is proposed to automatically search for optimalCNN architectures. GP-CNAS encodes CNNs as trees where leaf nodes (GPterminals) are selected residual blocks and non-leaf nodes (GP functions)specify the block assembling procedure. Our tree-based representation enableseasy design and flexible implementation of genetic operators. Specifically, wedesign a dynamic crossover operator that strikes a balance between explorationand exploitation, which emphasizes CNN complexity at early stage and CNNdiversity at later stage. Therefore, the desired CNN architecture with balanceddepth and width can be found within limited trials. Moreover, our GP-CNASframework is highly compatible with other manually-designed and NAS-generatedblock types as well. Experimental results on the CIFAR-10 dataset show thatGP-CNAS is competitive among the state-of-the-art automatic and semi-automaticNAS algorithms.

GP-CNAS: Convolutional Neural Network Architecture Search with Genetic Programming