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

When data is streaming from multiple sources, conventional training methodsupdate model weights often assuming the same level of reliability for eachsource; that is: a model does not consider data quality of each source duringtraining. In many applications, sources can have varied levels of noise orcorruption that has negative effects on the learning of a robust deep learningmodel. A key issue is that the quality of data or labels for individual sourcesis often not available during training and could vary over time. Our solutionto this problem is to consider the mistakes made while training on dataoriginating from sources and utilise this to create a perceived data qualityfor each source. This paper demonstrates a straight-forward and novel techniquethat can be applied to any gradient descent optimiser: Update model weights asa function of the perceived reliability of data sources within a wider dataset. The algorithm controls the plasticity of a given model to weight updatesbased on the history of losses from individual data sources. We show thatapplying this technique can significantly improve model performance whentrained on a mixture of reliable and unreliable data sources, and maintainperformance when models are trained on data sources that are all consideredreliable. All code to reproduce this work's experiments and implement thealgorithm in the reader's own models is made available.

Loss Adapted Plasticity in Deep Neural Networks to Learn from Data with Unreliable Sources