TalkChess.com

I implemented both methods and tested them now on 2x32 and 6x64 net. There doesn't seem to be much difference A0's policy head (as I understood it): 64 filters 3x3 convolution 73 filters 1x1 convolution (take the output directly) LCO's policy head: 73 filters 1x1 convolution 1858 dense layer The de...

I think that’s the major factor, especially at this TC, but “comtempt” (relatively dramatic cp scores) also plays a part...when possible I exclusively use win% with leela now because after a short time you can understand her evaluation in traditional “+-, +/-, +/=“, etc terms. If the cp value is in...

I’m about to discover if a 1070 in a laptop consuming a few watts only is effectively equivalent to the central heating and air conditioning version in a desktop. Hopefully last obstacle (cudnn versions not matching) shortly solved, then discovery ..... Eventually solved the cudnn problem, which wa...

I’m about to discover if a 1070 in a laptop consuming a few watts only is effectively equivalent to the central heating and air conditioning version in a desktop.

Hopefully last obstacle (cudnn versions not matching) shortly solved, then discovery .....

Is it the Hardware speed or some breakthrough programming innovation? So far what is the score between Komodo and Leela ? https://www.youtube.com/watch?v=ymDA7-hdkKA My answer is a bit different than others. Leela (following AlphaZero) has found a way to use a powerful GPU for chess, which is itsel...

Is it the Hardware speed or some breakthrough programming innovation? So far what is the score between Komodo and Leela ? https://www.youtube.com/watch?v=ymDA7-hdkKA My answer is a bit different than others. Leela (following AlphaZero) has found a way to use a powerful GPU for chess, which is itsel...

Is it the Hardware speed or some breakthrough programming innovation? So far what is the score between Komodo and Leela ? https://www.youtube.com/watch?v=ymDA7-hdkKA My answer is a bit different than others. Leela (following AlphaZero) has found a way to use a powerful GPU for chess, which is itsel...

Dann Corbit wrote: ↑

Thu Jan 17, 2019 12:01 am

chrisw wrote: ↑

Wed Jan 16, 2019 10:50 pm

Well a chess evaluating neural net is just a squashed and imperfect 32man egtb.

So is a chess player's brain, for that matter.

Yes, exactly. Knowledge is statistical. We know things because the thing worked for us in the past more often than not. Or somebody told us and we believed.

Is it the Hardware speed or some breakthrough programming innovation? So far what is the score between Komodo and Leela ? https://www.youtube.com/watch?v=ymDA7-hdkKA Nope, nobody can explain, there is no explanation, it just is. I can explain why that. First it understands nothing, no patterns, not...

Egbbdll now supports leela networks, which have policy head, as well besides value head. To use the lc0 networks, they should be converted to formats readable by egbbdll (i.e. either Protobuf (pb) format for Tensorflow backend, and UFF format for TensorRT support). The cpu version does not work yet...