Using neurons to build logical functions

Among other obscured parts of iOS and macOS SDK, there is one interesting library called SIMD. It is an interface for direct access to vector instructions and vector types, which are mapped directly to the vector unit in the CPU, without the need to write an assembly code. You can reference vector and matrix types as well as linear algebra operators defined in this header right from your Swift code, starting from 2.0 version.

Note

The universal approximation theorem states that a simple NN with one hidden layer can approximate a wide variety of continuous functions if proper weights are found. This is also commonly rephrased as NNs as universal function approximators. However, the theorem doesn't tell if it's possible to find such proper weights.

To get access to those goodies, you need to import simd in Swift files, or #include <simd/simd.h> in C/C++/Objective-C files. GPU also has SIMD units in it, so you can import SIMD into your metal shader...