Federated learning Archives

Continual learning in the federated-learning context

Federated learning is a process in which distributed devices, each with its own store of locally collected data, can contribute to a global machine learning model...

Events & Conferences2 years ago

Federated learning with weak supervision for speech recognition

Automatic-speech-recognition (ASR) models, which transcribe spoken utterances, are a key component of voice assistants. They are increasingly being deployed on devices at the edge of the...

Events & Conferences3 years ago

Personalized federated learning for a better customer experience

Federated learning (FL) is a framework that allows edge devices (e.g., Alexa devices) to collaboratively train a global model while keeping customers’ data on-device. A standard FL...

Events & Conferences3 years ago

Advances in trustworthy machine learning at Alexa AI

At Amazon, we take the protection of customer data very seriously. We are also committed to eliminating the biases that can exist in off-the-shelf language models...

Events & Conferences4 years ago

USC + Amazon Center on Secure and Trusted Machine Learning selects two PhD fellows

The USC + Amazon Center on Secure and Trusted Machine Learning, established in January 2021 to support fundamental research and development of new approaches to machine...