News for hackers. Stuff that matters.
Re:Solving Entry-Level Edge AI Challenges with Nvidia Jetson... by c_o_n_v_e_x on Wednesday September 21, 2022 @04:42AM (#32922285)
Out of curiosity, what use cases require training at the edge?
Re:Solving Entry-Level Edge AI Challenges with Nvidia Jetson... by fxtentacle on Wednesday September 21, 2022 @06:46AM (#32923196)
In my example, it is very helpful if you can adjust a speech model a bit to better match the user's dialect. So you don't train the full model, rather you just adjust the most coarse 5% of parameters in a pre-trained model by a tiny bit. But that can lead to great quality improvements at almost no additional cost.
Re:Solving Entry-Level Edge AI Challenges with Nvidia Jetson... by hasperdi on Wednesday September 21, 2022 @05:58AM (#32922824)
I'm no expert in ML, one use case is that if you want to refine the already trained model that was trained elsewhere.
Re:Solving Entry-Level Edge AI Challenges with Nvidia Jetson... by bravura on Wednesday September 21, 2022 @06:48AM (#32923212)
Additionally, privacy-preserving AI.