... we have a small favour to ask. More people, like you, are reading and supporting our blog: "Chess Engines Diary". And unlike many other sites and blogs, we made the choice to keep our articles open for all, regardless of where they live or what they can afford to pay.
We hope you will consider supporting us today. We need your support to continue to exist, because good entries are more and more work time. Every reader contribution, however big or small, is so valuable. Support "Chess Engines Diary" even a small amount– and it only takes a minute. Thank you. ================================================ My email: firstname.lastname@example.org
Fire 7.1 - new version best UCI chess engines!
Fire - UCI chess engine, Rating JCER=3185 author compilation - by Norman Schmidt
Leelenstein is a neural-network engine based on Lc0. But instead of self-play, it uses a net trained on select high-level engine games (“supervised learning”). It's training also included techniques such as squeeze excitation and learning rate schedulers. Leelenstein also includes non-Zero enhancements to the Lc0 binary, such as a trade penalty and mate scoring. Leelenstein 925 download
NNUE = efficiently updateable neural network backwards. Changes: Removed k-p_256x2-32-32 from the binary package. Added eval_nnue command. Thank you, tttak! Added a linker option to strip the binaries. Replaced the nn parameter file for halfkp_256x2-32-32. The nn parameter file was generated with the following commands. Stockfish NNUE 2020-07-06 download
Engine Powerbook 2020 - for analysis (and to play on Playchess.com, engine room). New version March 2020. Book options to play = Modus Optimal (Tournament book, Minimum games=3, Moves=35, Learn maximum) Engine Powerbook 2020 download