Month: August 2020

[From the last episode: We looked at some fundamental electrical concepts, with a focus on Ohm’s Law.] Having looked at Ohm’s Law, we’re now going to veer in a completely different direction. But not to worry: we’ll bring it all back together in a couple weeks. Before we can do […]

[From the last episode: We looked at some ways of optimizing neural-network so that they run better at the edge.] We’re going to cover one more interesting development in the world of AI, but in order for it to make any sense, we’re going to have to start by covering […]

[From the last episode: We looked at what it means to do machine learning “at the edge,” and some of the compromises that must be made.] When doing ML at the edge, we want two things: less computing (for speed and, especially, for energy) and smaller hardware that requires less […]

[From the last episode: We looked at activation and what they’re for.] We’ve talked about the structure of machine-learning (ML) models and much of the hardware and math needed to do ML work. But there are some practical considerations that mean we may not directly use the pristine model as […]