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

Identifying whether a given sample is an outlier or not is an important issuein various real-world domains. This study aims to solve the unsupervisedoutlier detection problem where training data contain outliers, but any labelinformation about inliers and outliers is not given. We propose a powerful andefficient learning framework to identify outliers in a training data set usingdeep neural networks. We start with a new observation called theinlier-memorization (IM) effect. When we train a deep generative model withdata contaminated with outliers, the model first memorizes inliers beforeoutliers. Exploiting this finding, we develop a new method called the outlierdetection via the IM effect (ODIM). The ODIM only requires a few updates; thus,it is computationally efficient, tens of times faster than otherdeep-learning-based algorithms. Also, the ODIM filters out outlierssuccessfully, regardless of the types of data, such as tabular, image, andsequential. We empirically demonstrate the superiority and efficiency of theODIM by analyzing 20 data sets.

ODIM: an efficient method to detect outliers via inlier-memorization effect of deep generative models