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

The goal of Machine Learning to automatically learn from data, extractknowledge and to make decisions without any human intervention. Such automatic(aML) approaches show impressive success. Recent results even demonstrateintriguingly that deep learning applied for automatic classification of skinlesions is on par with the performance of dermatologists, yet outperforms theaverage. As human perception is inherently limited, such approaches candiscover patterns, e.g. that two objects are similar, in arbitrarilyhigh-dimensional spaces what no human is able to do. Humans can deal only withlimited amounts of data, whilst big data is beneficial for aML; however, inhealth informatics, we are often confronted with a small number of data sets,where aML suffer of insufficient training samples and many problems arecomputationally hard. Here, interactive machine learning (iML) may be of help,where a human-in-the-loop contributes to reduce the complexity of NP-hardproblems. A further motivation for iML is that standard black-box approacheslack transparency, hence do not foster trust and acceptance of ML amongend-users. Rising legal and privacy aspects, e.g. with the new European GeneralData Protection Regulations, make black-box approaches difficult to use,because they often are not able to explain why a decision has been made. Inthis paper, we present some experiments to demonstrate the effectiveness of thehuman-in-the-loop approach, particularly in opening the black-box to aglass-box and thus enabling a human directly to interact with an learningalgorithm. We selected the Ant Colony Optimization framework, and applied it onthe Traveling Salesman Problem, which is a good example, due to its relevancefor health informatics, e.g. for the study of protein folding. From studies ofhow humans extract so much from so little data, fundamental ML-research alsomay benefit.

A glass-box interactive machine learning approach for solving NP-hard problems with the human-in-the-loop