arXiv:2409.03760cs.LG2024-09被引 1

不用反向传播也能让神经网络识别手写数字,准确率超80%。

Rethinking Deep Learning: Propagating Information in Neural Networks without Backpropagation and Statistical Optimization

  • 用阶跃函数构建无权重更新的全连接网络,直接传播信息。
  • 在MNIST上达到约80%准确率,证明无需优化也能有效传递信息。
  • 适合对生物神经机制模拟感兴趣的读者,启发新型计算范式。

发展强人工智能意味着技术奇点的到来,将极大推动人类文明进步并解决社会问题。神经网络(NNs)及其深度学习方法因模仿生物神经系统结构而被寄予厚望。然而,当前普遍使用的统计权重优化技术(如误差反向传播和损失函数)可能阻碍对真实神经系统的模拟。本研究探讨了神经网络作为神经结构模拟载体的信息传播能力与潜在应用,通过在修改版国家标准与技术研究院(MNIST)数据库上解决手写字符识别问题,不使用误差反向传播等统计优化方法。网络架构由采用阶跃函数作为激活函数的全连接层构成,含0-15个隐藏层,且无权重更新。准确率基于训练数据每类的平均输出向量与测试数据输出向量之间的向量相似性计算。结果表明,最高准确率约为80%,说明神经网络可在不依赖统计优化的情况下正确传播信息。此外,随着隐藏层数增加,准确率下降,这归因于输出向量方差减小,导致数据趋于平滑。该研究提出的神经网络结构与准确率计算方法简单,具有多种改进空间。此外,构建一个反复循环‘输入→处理→输出→环境响应→输入→…’的前馈神经网络,可能为实际软件应用铺平道路。

原文摘要 · Abstract (English)

Developing strong AI signifies the arrival of technological singularity, contributing greatly to advancing human civilization and resolving social issues. Neural networks (NNs) and deep learning, which utilize NNs, are expected to lead to strong AI due to their biological neural system-mimicking structures. However, the statistical weight optimization techniques commonly used, such as error backpropagation and loss functions, may hinder the mimicry of neural systems. This study discusses the information propagation capabilities and potential practical applications of NNs as neural system mimicking structures by solving the handwritten character recognition problem in the Modified National Institute of Standards and Technology (MNIST) database without using statistical weight optimization techniques like error backpropagation. In this study, the NNs architecture comprises fully connected layers using step functions as activation functions, with 0-15 hidden layers, and no weight updates. The accuracy is calculated by comparing the average output vectors of the training data for each label with the output vectors of the test data, based on vector similarity. The results showed that the maximum accuracy achieved is around 80%. This indicates that NNs can propagate information correctly without using statistical weight optimization. Additionally, the accuracy decreased with an increasing number of hidden layers. This is attributed to the decrease in the variance of the output vectors as the number of hidden layers increases, suggesting that the output data becomes smooth. This study's NNs and accuracy calculation methods are simple and have room for various improvements. Moreover, creating a feedforward NNs that repeatedly cycles through 'input -> processing -> output -> environmental response -> input -> ...' could pave the way for practical software applications.

神经网络无反向传播信息传播MNIST

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。