用公式计算权重的神经网络比随机初始化训练更快更稳定。
A comparative analysis of a neural network with calculated weights and a neural network with random generation of weights based on the training dataset size
- 权重通过公式直接计算，无需随机初始化
- 数据量减少时性能下降更少，训练速度显著提升
- 适合小样本场景或需要快速部署的应用
本文研究了多层感知机神经网络在度量识别任务中的能力，其中权重通过解析公式预先计算。针对不同大小的MNIST训练数据集，进行了预计算权重网络与随机初始化权重网络的对比实验。结果表明，采用预计算权重的多层感知机能够实现更快的训练速度，并对训练数据量减少表现出更强的鲁棒性。
原文摘要 · Abstract (English)
The paper discusses the capabilities of multilayer perceptron neural networks implementing metric recognition methods, for which the values of the weights are calculated analytically by formulas. Comparative experiments in training a neural network with pre-calculated weights and with random initialization of weights on different sizes of the MNIST training dataset are carried out. The results of the experiments show that a multilayer perceptron with pre-calculated weights can be trained much faster and is much more robust to the reduction of the training dataset.
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。