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.Link to the paper, the full 6502 source code, and a video demo.https://jarnoh.github.io/mnist64/paper.pdfhttps://github.com/jarnoh/mnist64https://youtu.be/Z_S0IZenW_EI'm interested to hear your feedback and hoping for someone to beat these numbers! Comments URL: https://news.ycombinator.com/item?id=49767689 Points: 1 # Comments: 0