@inbook{f036764dd65c40b08dd28fe7c551de2c,
title = "Federated Data Model - Go Local, Go Global and Go Fusion: In an Industry 4.0 Context",
abstract = "To set the main data model further in perspective and focus the authors continue with data interoperability and data pattern recognition before summarizing the chapter. In terms of federated learning and having a central data model copied over to local devices, the central data model needs to understand the local particulars if it is not just constrained to repetitive redundant tasks. If we extend the complexity of the data model, it also should be able to understand its environmental context. An emphasis is to be aware of how federated learning with ML and its data model may exclude reflective capacity where we may use cognitive software models such as ACT-R, BDI, etc., to cover these behaviors. The authors have discussed how Federated Learning and a local data model on an edge device needs to be understood at a central aggregated level to not lose local or global awareness on when to fuse disparate data to build a holistic data model.",
keywords = "Federated Learning",
author = "Daniel Einarson and Charlotte Sennersten",
note = "Publisher Copyright: {\textcopyright} 2024 Saravanan Krishnan, A. Jose Anand, R. Srinivasan, R. Kavitha and S. Suresh.",
year = "2023",
month = nov,
day = "16",
doi = "10.1201/9781003384854-2",
language = "English",
isbn = "9781032471624",
pages = "32--60",
editor = "Krishnan, {Saravanan } and Anand, { A. Jose } and Srinivasan, {R. } and R. Kavitha and S. Suresh",
booktitle = "Handbook on Federated Learning",
publisher = "CRC Press",
edition = "1",
}