How Data Scientists Use Federated Learning to Protect Privacy
from The Data Science Podcast with Fexingo: Analytics, Machine Learning, and Data-Driven Conversations Hosted by Fexingo
Episode 53 of The Data Science Podcast dives into federated learning — a technique that trains machine learning models across decentralized data without ever moving sensitive information to a central server. Lucas and Luna break down how Google used it to improve keyboard predictions on Gboard without seeing what you type, and how Apple applies it to Siri without uploading your voice. They discuss the key trade-off: better privacy versus slightly worse model accuracy, and why an open-source framework like TensorFlow Federated is making the approach accessible. They also explore real-world adoption — from hospitals training diagnostic models without sharing patient records to banks detecting fraud across institutions without exposing transaction histories. By the end, you will understand why the phrase 'bring the model to the data, not the data to the model' is reshaping privacy in machine learning. #FederatedLearning #PrivacyPreservingML #DataScience #MachineLearning #Google #Apple #Gboard #Siri #TensorFlowFederated #HealthcareAI #FederatedAveraging #OnDeviceAI #DifferentialPrivacy #SecureAggregation #Technology #FexingoBusiness #BusinessPodcast #Podcast Keep every episode free: buymeacoffee.com/fexingo
Embed this episode
No transcript yet.