Original Summary

I built an 8-bit binarized convolutional neural network that recognizes handwritten digits on C64 with state-of-the-art accuracy. I also designed a cascade model to get interactive response, and implemented everything with self-modifying cycle optimized 6502 assembly - resulting 0.653s average inference time.<p>Link to the paper, the full 6502 source code, and a video demo.<p><a href="https:&#x2F;&#x2F;jarnoh.github.io&#x2F;mnist64&#x2F;paper.pdf" rel="nofollow">https:&#x2F;&#x2F;jarnoh.github.io&#x2F;mnist64&#x2F;paper.pdf</a><p><a href="https:&#x2F;&#x2F;github.com&#x2F;jarnoh&#x2F;mnist64" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;jarnoh&#x2F;mnist64</a><p><a href="https:&#x2F;&#x2F;youtu.be&#x2F;Z_S0IZenW_E" rel="nofollow">https:&#x2F;&#x2F;youtu.be&#x2F;Z_S0IZenW_E</a><p>I&#x27;m interested to hear your feedback and hoping for someone to beat these numbers!

  • 情报分类：商业与市场研究
  • 分类依据：内容涉及商业、投资或市场动态
  • 信息来源：Hacker News 新项目
  • 发布时间：2026/9/20 00:07:01