One-Shot Federated Learning with Neuromorphic Processors
This work addresses the challenge of low-power, privacy-preserving machine learning for mobile devices using neuromorphic hardware, though it appears incremental by applying federated learning to a new processor type.
The paper tackled the problem of enabling efficient and private collaborative learning on neuromorphic processors, achieving state-of-the-art accuracy on a one-shot learning gesture recognition task.
Being very low power, the use of neuromorphic processors in mobile devices to solve machine learning problems is a promising alternative to traditional Von Neumann processors. Federated Learning enables entities such as mobile devices to collaboratively learn a shared model while keeping their training data local. Additionally, federated learning is a secure way of learning because only the model weights need to be shared between models, keeping the data private. Here we demonstrate the efficacy of federated learning in neuromorphic processors. Neuromorphic processors benefit from the collaborative learning, achieving state of the art accuracy on a one-shot learning gesture recognition task across individual processor models while preserving local data privacy.