Changes

The [[Neural Networks|neural network]] version of Scorpio '''2.9.0''' (2019) works using '''[[Scorpio#Bitbases|egbbdll''' ]] shared library <ref>[https://github.com/dshawul/egbbdll GitHub - dshawul/egbbdll: Probing code for scorpio bitbases]</ref> that provides neural network inference via [https://en.wikipedia.org/wiki/TensorFlow TensorFlow] and/or ''TensorRT'' <ref>[https://developer.nvidia.com/tensorrt NVIDIA TensorRT | NVIDIA Developer]</ref> backends <ref>[https://github.com/dshawul/Scorpio#nns GitHub - dshawul/Scorpio: Scorpio chess engine - Neural Networks (NNs)]</ref>. ==ScorpioNNUE==With the the advent of [[NNUE]] and its huge success in [[Stockfish NNUE]], [[CFish#NNUE|CFish NNUE]] and other engines, [[Daniel Shawul]] added NNUE support à la CFish into his [[Scorpio#Bitbases|egbbdll]] probing library <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=7&t=75400&start=22 Re: Hacking around CFish NNUE] by [[Daniel Shawul]], [[CCC]], October 15, 2020</ref>, and reported more than 400 Elo out of his implementation with a shared library with Scorpio '''3.0.9''' <ref>[http://www.talkchess.com/forum3/viewtopic.php?f=7&t=75415&start=3 Re: How to scale stockfish NNUE score?] by [[Daniel Shawul]], [[CCC]], October 17, 2020</ref>.