> For the complete documentation index, see [llms.txt](https://stockfish.mineta.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://stockfish.mineta.dev/nnue/readme.md).

# Experiments

#### [Experiment 1](/nnue/readme/experiment-1.md)

Use 32 PSQT buckets and layer stacks for SmallNet.

Status: <mark style="color:red;">FAILED</mark>

#### [Experiment 2](/nnue/readme/experiment-2.md)

Use 16 PSQT buckets and layer stacks for SmallNet.

Status: <mark style="color:red;">FAILED</mark>

#### [Experiment 3](/nnue/readme/experiment-3.md)

SmallNet L1=256, simple\_eval threshold 600

Status: <mark style="color:red;">FAILED</mark>

#### [Experiment 4](/nnue/readme/experiment-4.md)

Add L0 smooth regularization during SmallNet training.

Status: <mark style="color:red;">FAILED</mark>
