Neural Network Architecture

Overview

NIKOLA uses a state-of-the-art Efficiently Updatable Neural Network (NNUE) for position evaluation. Unlike traditional hand-crafted evaluation functions, NNUE learns complex positional patterns from millions of high-quality games and engine self-play.

HalfKA Architecture

NIKOLA employs the HalfKA (Half-King-All) feature set, which encodes:

• King position - Relative location of each side's king
• Piece placement - All pieces indexed relative to king position
• Perspective - Separate views for white and black

This representation enables efficient incremental updates as pieces move, requiring only sparse matrix operations rather than full network evaluation.

Network Topology

GPU Acceleration

NIKOLA's neural network inference is fully GPU-accelerated using native MIND tensor operations. Key optimizations include:

• Batched inference - Evaluate multiple positions simultaneously
• Tensor cores - Utilize FP16/BF16 mixed precision on supported GPUs
• Memory pooling - Minimize allocation overhead during search
• Async execution - Overlap compute with memory transfers

Supported GPU Architectures

Incremental Updates

The NNUE architecture enables "efficiently updatable" evaluation. When a move is made, only the affected features need recalculation rather than the entire network. This provides 10-100x speedup compared to full evaluation, critical for deep search.

Training Data

NIKOLA's network is trained on a proprietary dataset of over 10 billion positions generated through:

• Self-play games at various time controls
• High-depth analysis of master games
• Curated endgame positions from tablebases
• Adversarial positions designed to expose weaknesses

setoption name NNUEPath value /path/to/custom.nnue