The rapid build-out of AI on the edge marks a fundamental shift in where intelligence is located, how much is included in devices, and the speed at which that intelligence can be applied to everyday problems. While the cloud will still be used for training large language models, the edge will include a collection of smaller, much more targeted language models. Nigel Drego, CTO and co-founder of Quadric, talks about how edge AI will interact with the cloud in co-optimized systems, how the proliferation of edge AI will improve response time and reduce privacy concerns, and how quickly this market is expanding. [According to recent estimates, 100 billion models are being run locally on edge devices today.]
https://www.youtube.com/embed/rrke8kXnsII
The post Redefining Roles For Edge And Cloud AI appeared first on Semiconductor Engineering.
Source: https://semiengineering.com/redefining- ... -cloud-ai/