Computer-Generated Chess Problem 03015

This is an original 'KQNN vs krn' three-move chess problem generated autonomously by a computer using the Digital Synaptic Neural Substrate (DSNS) computational creativity approach. The DSNS does not use endgame tablebases, neural networks or any kind of machine learning found in traditional artificial intelligence (AI). It also has nothing to do with deep learning.

8/1N6/8/8/1N1r4/k7/8/Kn2Q3 w - - 0 1
White to Play and Mate in 3
Chesthetica v11.82 (Selangor, Malaysia)
Generated on 11 Aug 2020 at 7:53:41 AMSolvability Estimate = Difficult
Most changes to Chesthetica that result in a slightly higher 'version number' are simply to improve the interface, by the way. Get a glimpse into the 'mind' of a computer composer. Leave a comment below, if you like. Solving chess puzzles like this is probably good for your health as it keeps your brain active. Nobody wants something like early-onset Alzheimer's.
Solution