読書リサーチレーダー投資フレームワーク
ログイン / 新規登録
← 読解に戻る
ニューストピック · Doomformerクイックテイク1 分で読めるDisconfirmAI 編集部

Developer Releases Doomformer: Compiling Integer Neural Networks into DOOM Maps Achieves 97.16% MNIST Accuracy

Open-source project Doomformer runs neural networks inside DOOM maps using game mechanics, achieving 97.16% accuracy on MNIST digits with zero-tolerance verification against NumPy.

検証済み 2026-10-31 06:17 GMT+8

GitHub user mottopanikeiku has released Doomformer, an open-source project that compiles integer neural networks into map files for the classic first-person shooter DOOM. According to t3n.de and the GitHub repository, the experiment uses "Voodoo Dolls" (cloned player entities spawned when entering specific areas) as computational units, storing values in light levels and floor heights to perform neural network inference.

In tests on the MNIST handwritten digit dataset, Doomformer used a map network containing 1,355 Voodoo Dolls to identify 10,000 test samples, correctly recognizing 9,716 digits for an accuracy of 97.16%. The float model version achieved 97.58%. The project emphasizes strict verification: every value computed by the game engine is compared against integer reference results from NumPy with zero tolerance.

The core innovation lies in its compiler technique, which maps neural network layers to game map elements: input values correspond to crowds of dolls, weights to lines crossed by dolls, activation functions (ReLU) to staircase gates dolls must climb, and attention mechanisms to dolls squeezing under lowered ceilings. While demonstrating the feasibility of non-traditional computational substrates, the method is extremely slow—a small MLP runs about 23,000 times slower than NumPy—and currently supports only integer models without modern architecture components like LayerNorm.

ソース

ログイン / 新規登録
読書リサーチレーダー投資フレームワーク
github.com
GitHub
↗
  • t3n.de↗
  • トピック

    Doomformer

    开发者mottopanikeiku发布开源项目Doomformer,将整数神经网络编译进《毁灭战士》(DOOM)地图中运行。该项目利用游戏机制中的“巫毒娃娃”(Voodoo Dolls)、地板线条和光照等级来模拟神经网络的权重、激活函数和计…

    4 ステップ1 件更新日 2026-11-01 17:36

    経緯

    1. 2026-10-28GitHub仓库发布v0.7.1版本,修复了静态提取器在特定地图配置下的误报问题,并优化了调度与成本文档。github.com ↗
    2. 2026-10-30德国科技媒体t3n.de报道Doomformer项目,介绍其如何利用1,355个巫毒娃娃在单张地图中运行MNIST网络。t3n.de ↗
    3. 2026-10-30AI Weekly发布分析文章,指出Doomformer在10,000个测试样本中正确识别9,716个数字,准确率为97.16%,但运行速度极慢。aiweekly.co ↗

    未解決の問題

    • Doomformer目前仅支持整数运算且不支持LayerNorm,未来是否会扩展至更复杂的浮点或Transformer架构?
    • 开发者提到正在实验让AI自己玩DOOM,但目前决策耗时约22秒,该实时交互性能是否有优化空间?
    • 除了MNIST分类,Doomformer在生成式任务(如文本生成)上的实际可用性如何?
    トピック全文を読む →
    リサーチを続ける →