不训练直接算出卷积神经网络权重，10张图就能识别手写数字。
Analytical Calculation of Weights Convolutional Neural Network
- 基于10张MNIST图像，纯解析计算网络权重与通道数。
- 无需训练即可识别超500张测试图像，推理快于1秒。
- 适合快速部署、无训练资源的分类场景。
本文提出一种无需标准训练过程的卷积神经网络（CNN）权重与阈值解析计算算法。仅需从MNIST数据集选取10张图像（每类数字一张），即可通过该方法确定网络参数，并解析推导各层通道数。使用C++ Builder实现软件模块，在MNIST数据集上开展实验。结果表明，经解析计算的CNN在未进行任何训练的情况下，可识别超过500张手写数字图像，推理时间仅为若干毫秒。研究证明，仅通过解析计算即可构建并直接应用CNN进行分类任务，无需传统训练流程。
原文摘要 · Abstract (English)
This paper presents an algorithm for analytically calculating the weights and thresholds of convolutional neural networks (CNNs) without using standard training procedures. The algorithm enables the determination of CNN parameters based on just 10 selected images from the MNIST dataset, each representing a digit from 0 to 9. As part of the method, the number of channels in CNN layers is also derived analytically. A software module was implemented in C++ Builder, and a series of experiments were conducted using the MNIST dataset. Results demonstrate that the analytically computed CNN can recognize over half of 1000 handwritten digit images without any training, achieving inference in fractions of a second. These findings suggest that CNNs can be constructed and applied directly for classification tasks without training, using purely analytical computation of weights.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。