Nerual Network of Stochastic Computing for MNIST Recognition. This project is the part of the redstonic convolutional neural network in Minecraft. We built the world first redstonic convolutional neural network, the task being the recognition of 15×15 hand-written digits. LeNet-5 as its architecture, the network can achieve an accuracy up to 80%. We used an unconventional computational method, the stochastic computing, to realize the network, making it much simpler in design and layout compared to the traditional full-precision computing. The recognition time is 5 minutes per figure theoretically. However, limited by the computational capacity of Minecraft, the real running time exceeds 20 minutes. Nevertheless, it is a breakthrough in redstonic digital circuits, and it may inspire real-world physical neural networks.

We are so sorry that we cannot provide a proper and clear organized codes due to limited ability and time.

Video link in bilibili.

随机计算用于手写数字识别。我们搭建了世界首个红石卷积神经网络，任务是识别15×15手写数字。该网络使用LeNet-5架构，准确率可达80%。我们使用非传统的计算方式——随机计算来实现神经网络，使得设计和布局上比传统的全精度计算简单许多，且单次理论识别时间仅为5分钟。受限于Minecraft的运算能力，实际识别时间超过20分钟。尽管如此，这仍是红石数电领域的重大突破，也可能启发现实中的硬件神经网络。

由于时间成本和精力有限，我们很抱歉没法提供清晰的便于查阅的项目代码。

视频链接