Last year, Google introduced a new neural networks API in Android 8.1 Oreo that provided developers with hardware-backed tools for machine learning. Now, with Android P, Google is expanding the API to support nine new operations. Pixel 2 devices will also have support for Qualcomm's Hexagon HVX driver, giving developers further improvements in performance on those devices. 

At the time, Google's neural network API supported on-device model creation, compilation, and execution, meaning you could not only build a model as required on the device, but you could also run it. Now Google is adding a bunch of new tools for neural networks in Android P: "Pad, BatchToSpaceND, SpaceToBatchND, Transpose, Strided Slice, Mean, Div, Sub, and Squeeze."

I'll be honest, I have no idea what those specific operations mean, but an expansion in related API tools will surely come in handy for developers building on-device machine learning systems. The added acceleration via Qualcomm's Hexagon DSP "Vector eXtensions" should significantly improve performance for developers as well.