Differentiable Swift is an experimental language feature that is currently being pitched as part of the Swift Evolution process in “Differentiable programming for gradient-based machine learning”.

Larry Weber, Chief Operations Officer at PassiveLogic, will be speaking at the Realcomm | IBcon Real Estate Conference and Expo 2022 on Tuesday, June 14th in Orlando, Florida.

In Part 3, we got a feel for the AutoDiff API. Now let’s go a little deeper.

Let’s get a feel for how to use it beyond a trivial example. In order to do so, we’ll need to understand a few things about how it works.

HVAC systems come in a seemingly infinite number of shapes and sizes. At PassiveLogic, we are building our Innovation Center as a test platform to validate our solution across as many possible system configs as we can.

So now we understand how to optimize a function with Gradient Descent, as long as we can get the derivative of the function. Great, if all functions had an obvious derivative, we would be able to optimize everything!

Automatic differentiation is an exciting emerging technology which enables deep learning applications and is of particular value to PassiveLogic’s smart building platform.

Kepler Ridge is our lead builder for PassiveLogic’s Innovation Center. He spent the first few years of his career shifting between a path in plumbing vs one in software engineering — but here at PassiveLogic, he can do both.

In Part 0 of this series, we introduce the usefulness of automatic differentiation.

What if code could run, not just forwards, but backwards too? While automatic differentiation isn’t exactly reversible computing, it’s a close proxy for solving the large number of computing problems that take the form of: “I have the answer… what was the question?”