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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Deep Convolutional Neural Networks (DCNN) has shown excellent performance ina variety of machine learning tasks. This manuscript presents DeepConvolutional Neural Fields (DeepCNF), a combination of DCNN with ConditionalRandom Field (CRF), for sequence labeling with highly imbalanced labeldistribution. The widely-used training methods, such as maximum-likelihood andmaximum labelwise accuracy, do not work well on highly imbalanced data. Tohandle this, we present a new training algorithm called maximum-AUC forDeepCNF. That is, we train DeepCNF by directly maximizing the empirical AreaUnder the ROC Curve (AUC), which is an unbiased measurement for imbalanceddata. To fulfill this, we formulate AUC in a pairwise ranking framework,approximate it by a polynomial function and then apply a gradient-basedprocedure to optimize it. We then test our AUC-maximized DeepCNF on three verydifferent protein sequence labeling tasks: solvent accessibility prediction,8-state secondary structure prediction, and disorder prediction. Ourexperimental results confirm that maximum-AUC greatly outperforms the other twotraining methods on 8-state secondary structure prediction and disorderprediction since their label distributions are highly imbalanced and also havesimilar performance as the other two training methods on the solventaccessibility prediction problem which has three equally-distributed labels.Furthermore, our experimental results also show that our AUC-trained DeepCNFmodels greatly outperform existing popular predictors of these three tasks.

AUC-maximized Deep Convolutional Neural Fields for Sequence Labeling