Federated Learning

Federated learning is a cutting-edge machine learning technique that enables collaborative model training across multiple decentralized data sources while preserving data privacy. Coursera's Federated Learning catalogue teaches you the fundamental concepts and practical implementation of this innovative approach, emphasizing its applications in privacy-sensitive domains. You'll learn to design and deploy federated learning systems, implement secure aggregation protocols, and address challenges such as data heterogeneity and communication efficiency. By mastering federated learning, you'll be empowered to develop privacy-preserving AI solutions for industries like healthcare, finance, and telecommunications, opening up new opportunities in the rapidly evolving field of distributed machine learning.

Filter by

Subject
Required

Language
Required

The language used throughout the course, in both instruction and assessments.

Learning Product
Required

Learn from top instructors with graded assignments, videos, and discussion forums.
Get in-depth knowledge of a subject by completing a series of courses and projects.

Level
Required

Duration
Required

Subtitles
Required

Educator
Required

Hands-on Learning
Required

Results for "Federated Learning"

  • Skills you'll gain: Cryptography, Encryption, Network Security, Cybersecurity, Security Engineering, Network Protocols, Federated Learning, Data Integrity, Security Management

  • From the course: 6G Evolution: Blockchain, Semantic Communications & Radar·Lesson: Section 2: Reliably Unreliable: Rethinking Wireless Networks

  • From the course: Customising your models with TensorFlow 2·Lesson: Introduction to the course

  • University of Glasgow

    Skills you'll gain: Federated Learning, Wireless Networks, Emerging Technologies, Digital Communications, Communication Systems, Blockchain, Internet Of Things, Network Security, Telecommunications, Network Performance Management, Network Planning And Design, Zero Trust Network Access, Computer Vision, Artificial Intelligence and Machine Learning (AI/ML), Electrical Engineering, Network Analysis, Information Technology, Electronics Engineering, Machine Learning, Trustworthiness

  • Skills you'll gain: Model Evaluation, Deep Learning, Descriptive Analytics, Data Ethics, Data Preprocessing, ICD Coding (ICD-9/ICD-10), Federated Learning, Autoencoders, Health Informatics, Clinical Data Management, Medical Records, Data Mining, Medical Coding, Decision Intelligence, Electronic Medical Record System, Responsible AI, AI Security, Electronic Medical Record, Clinical Informatics, Machine Learning

  • From the course: Clinical Decision Support Systems·Lesson: Federated Learning and defences against privacy attacks

  • From the course: Human Factors in AI·Lesson: Privacy and AI

  • From the course: 6G Evolution: Blockchain, Semantic Communications & Radar·Lesson: Section 3: Future Directions and Challenges

  • From the course: 6G Vision: ML, Intelligent Surfaces & Optical Networks·Lesson: Section 5: AI for 6G and 6G for AI

  • From the course: 6G Evolution: Blockchain, Semantic Communications & Radar·Lesson: Section 2: Vision aided Wireless Networks

  • From the course: 6G Vision: ML, Intelligent Surfaces & Optical Networks·Lesson: Section 4: Interplay of Machine Learning and Reconfigurable Intelligent Surfaces

  • University of Glasgow

    From the course: 6G Evolution: Blockchain, Semantic Communications & Radar