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

Recently sequential model based optimization (SMBO) has emerged as apromising hyper-parameter optimization strategy in machine learning. In thiswork, we investigate SMBO to identify architecture hyper-parameters of deepconvolution networks (DCNs) object recognition. We propose a simple SMBOstrategy that starts from a set of random initial DCN architectures to generatenew architectures, which on training perform well on a given dataset. Using theproposed SMBO strategy we are able to identify a number of DCN architecturesthat produce results that are comparable to state-of-the-art results on objectrecognition benchmarks.

Hyper-parameter optimization of Deep Convolutional Networks for object recognition