publication . Conference object . 2019

Explainable Deep Neural Networks for Multivariate Time Series Predictions.

Roy Assaf; Anika Schumann;
Open Access
  • Published: 01 Jul 2019
<jats:p>We demonstrate that CNN deep neural networks can not only be used for making predictions based on multivariate time series data, but also for explaining these predictions. This is important for a number of applications where predictions are the basis for decisions and actions. Hence, confidence in the prediction result is crucial. We design a two stage convolutional neural network architecture which uses particular kernel sizes. This allows us to utilise gradient based techniques for generating saliency maps for both the time dimension and the features. These are then used for explaining which features during which time interval are responsible for a giv...
free text keywords: Machine Learning [AI], Knowledge Representation [AI], Energy [Reasoning Applications]
Funded by
Reliable OM decision tools and strategies for high LCoE reduction on Offshore wind
  • Funder: European Commission (EC)
  • Project Code: 745625
  • Funding stream: H2020 | IA
Download fromView all 2 versions
Conference object . 2019
Provider: ZENODO
Conference object . 2019
Provider: Crossref
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue