Federated Learning explained in 90 seconds – Privacy-Preserving AI
Convert Text to Speech
Artificial Intelligence is largely reliant on data aggregation to work, and that in itself presents a challenge. How do companies preserve data privacy throughout the aggregation process while still remaining efficient? That’s where XAIN’s Federated Learning technology comes in.
Instead of training, aggregating, and storing data on one centralised processing unit, Federated Machine Learning trains AI models at each dataset separately. The findings from each separate AI model are communicated and aggregated with the findings of the other datasets, but only the aggregations are stored together. That means each individual dataset remains private and there is no need to anonymize or store local data in a central source. This reduces integration and training costs, simplifying the data training process without compromising the privacy of local datasets.
Learn more on the XAIN Website → https://xain.io
Find out what lawyers say regarding XAINs GDPR compliance → https://www.xain.io/assets/XAIN-Legal-Opinion.pdf
Dive deeper into XAINs technology and learn about use cases → https://www.xain.io/assets/XAIN-Whitepaper.pdf
Explore our repo on Github. The XAIN platform is open source → https://github.com/xainag/xain
Follow us!
LinkedIn: https://www.linkedin.com/company/xain_ag/
Twitter: @XAIN_AG https://twitter.com/XAIN_AG
Medium: https://medium.com/xain
XAIN AG aims to solve challenges in the research field of privacy-preserving AI, particularly focusing on Federated Learning. In 2017, XAIN won the 1st Porsche Innovation Contest and was named one of Germany’s most innovative startups by Forbes Magazine one year later.
source
0 Responses to Federated Learning explained in 90 seconds – Privacy-Preserving AI