Pairwise Gaussian Loss for Convolutional Neural Networks
IEEE Transactions on Industrial Informatics(2020)
摘要
Convolutional neural networks (CNNs) have demonstrated great competence in feature representation, and then, achieved a good performance to many classification tasks. Cross-entropy loss, together with softmax, is arguably one of the most commonly used loss functions in CNNs (that is generally called softmax loss). However, the softmax loss can result in a weakly discriminative feature representati...
更多查看译文
关键词
Training,Neural networks,Computer architecture,Loss measurement,Convergence,Feature extraction,Organizations
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要