Training on Mobile and Edge Devices Could Improve the User Experience While Preserving Privacy
We’ve all had those frustrating experiences with our mobile phones when the voice assistant seems to possess artificial stupidity instead of artificial intelligence. The real problem here is that these assistants require cloud connectivity (increasing latency) and do not continuously learn from interactions with you over time. Qualcomm AI Research shows how to change that by adding on- device learning capabilities to mobile and edge devices, enabling personalization while preserving privacy.
Let’s take a closer look. You can download this exclusive Cambrian AI mini-brief by clicking below.
Table Of Contents
- Introduction
- THE CHALLENGE AND OPPORTUNITY OF ON-DEVICE LEARNING
- FEW-SHOT LEARNING
- FEDERATED LEARNING (FL)
- BACKPROPAGATION OPTIMIZATION
- Conclusions