ECML PKDD 2018 Workshops

This book constitutes revised selected papers from the workshops DMLE and IoTStream, held at the 18thEuropean Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2018, in Dublin, Ireland, in September 2018.
The 8 full papers presented in this volume were carefully reviewed and selected from a total of 12 submissions. The workshops included are: DMLE 2018: First Workshop on Decentralized Machine Learning at the Edge IoTStream 2018: 3rd Workshop on IoT Large Scale Machine Learning from Data Streams

Inhalt
Decentralized Machine Learning on the Edge. - Sparsity in Deep Neural Networks---An Empirical Investigation with TensorQuant. - Asynchronous Federated Learning for Geospatial Applications. - Generalizing Knowledge in Decentralized Rule-based Models. - Introducing Noise in Decentralized Training of Neural Networks. - Query Log Analysis: Detecting Anomalies in DNS Traffic at a TLD Resolver. - Multimodal Tweet Sentiment Classification Algorithm Based on Attention Mechanism. - Active Learning by Clustering for Drifted Data Stream Classification. - Self Hyper-Parameter Tuning for Stream Recommendation Algorithms. - Deep Online Storage-Free Learning on Unordered Image Streams. - Fault Prognostics for the Predictive Maintenance of Wind Turbines: State of the Art.