Madeleine Birchfield wrote: ↑Sat Nov 14, 2020 8:40 am
I was a big Leela fan back in 2018 and believed it was going to become the strongest chess engine on the scene and it was superior to traditional engines due to its strong positional evaluation that handcrafted evaluations simply cannot replicate, but I largely saw the neural network thing as something that was largely incompatible with the traditional alpha-beta search paradigm, due to the fact that no traditional engine supports the use of GPUs. So for me, it was more a fact of how many people were willing to shift away from the traditional paradigm over to the Leela-style paradigm using GPUs, and nobody, aside from Daniel Shawul with Scorpio, seemed interested in moving to the new Leela-style paradigm, so I concluded that it would be a very long time until traditional engines adopted neural networks.
dragontamer5788 wrote: ↑Wed Nov 06, 2019 6:14 am
A few weeks ago, I theorized that GPUs can effectively perform work-efficient alpha-beta search. It led to a long discussion elsewhere on the internet, which pretty much ended with "If you think its possible, then you should do it". A couple of weeks later, here I am today ready to learn from the Chess community and begin tackling this project.
This was one of the things I was hoping would take off in the computer chess community, as I saw it as a prerequisite for traditional alpha-beta engines to be compatible with neural networks, but it never got anywhere, and was eventually superseded by NNUE.
turns out the answer is a little more than three years for Stockfish and three and a half years for Komodo. Possibly two and a half years if the computer chess community did not ignore NNUE when it first came out.
Fat Titz by Stockfish, the engine with the bodaciously big net. Remember: size matters. If you want to learn more about this engine just google for "Fat Titz".