For the ones interested I would like to announce that there is available for download the first version of "1 Ply Engine" based on the SlyMlego platform at the link:

This is a release oriented to developers and machine learning enthusiasts and not to general public. It has been developed and tested on Linux (even if mostly should work also on Windows/Mac/etc where Keras and TF are available).

Like the more famous AlphaZero from Google this engine uses a residual artificial neural network architecture. Differences are that it has been trained in a supervised way (with Stockfish as the trainer) instead of using the reinforcement learning approach, the size is just of 4 layers instead of 40, there is no tree search at all, and currently there is just the value network in place.

This particular engine has been implemented not to be strong, but to show the very raw ANN evaluation of a single position: the engine "horizon" is in fact just the move it's playing (hence the name), so for example can leave the queen to be freely captured since not even the very first counter move is evaluated! Taking into consideration this, and that it has absolutely no explicit logic in the code (opening / endgame / ordering / tree search / etc), and that the network has still to be optimized, the engine shows to understand anyway pretty well the position!!

In the future there are the evaluations of more network architectures and integration of the evaluation function in a "standard" engine (a ready Python one might be a good choice as for example PyChess or Sunfish, if they'll be able to manage a slow but powerful evaluation).

Hope you like and you'll find it an easy chess platform to experiment with neural networks!

Personally I will go on with exploring a DenseNet architecture efficiency, trying to implement the policy network, and evolving the engine capabilities. In the meantime: happy hacking and happy chess to everyone! :)