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

Artificial neural networks (ANNs) are known to be powerful methods for manyhard problems (e.g. image classification, speech recognition or time seriesprediction). However, these models tend to produce black-box results and areoften difficult to interpret. Layer-wise relevance propagation (LRP) is awidely used technique to understand how ANN models come to their conclusion andto understand what a model has learned. Here, we focus on Echo State Networks(ESNs) as a certain type of recurrent neural networks, also known as reservoircomputing. ESNs are easy to train and only require a small number of trainableparameters, but are still black-box models. We show how LRP can be applied toESNs in order to open the black-box. We also show how ESNs can be used not onlyfor time series prediction but also for image classification: Our ESN modelserves as a detector for El Nino Southern Oscillation (ENSO) from sea surfacetemperature anomalies. ENSO is actually a well-known problem and has beenextensively discussed before. But here we use this simple problem todemonstrate how LRP can significantly enhance the explainablility of ESNs.

Layer-wise Relevance Propagation for Echo State Networks applied to Earth System Variability