Exclaim
发表于 2025-3-28 17:58:53
Adversarial Robustness of Multi-bit Convolutional Neural Networks, with a slight degradation of natural accuracy (–2.4pp) when compared to a 2-bit fixed-point quantized implementation of ResNet-20 on CIFAR-10. Similar observations hold for deeper and wider ResNets trained on different datasets, such as CIFAR-100 and ImageNet. Second, this work shows that the defen
盖他为秘密
发表于 2025-3-28 20:03:51
http://reply.papertrans.cn/48/4701/470030/470030_42.png
CRUMB
发表于 2025-3-29 02:22:13
Grouping Shapley Value Feature Importances of Random Forests for Explainable Yield Prediction, algorithm to compute them efficiently on tree structures. We provide a blueprint for designing swarm plots that combine many local explanations for global understanding. Extensive evaluation of two different yield prediction problems shows the worth of our approach and demonstrates how we can enabl
微不足道
发表于 2025-3-29 06:16:13
http://reply.papertrans.cn/48/4701/470030/470030_44.png
预测
发表于 2025-3-29 07:27:25
http://reply.papertrans.cn/48/4701/470030/470030_45.png
ABHOR
发表于 2025-3-29 13:39:02
Application of Mean-Variance Cloning Technique to Investigate the Comparative Performance Analysis ence the computational time of the classifiers. The results revealed that the Fisher linear classification method (FLCM) performed comparably for imbalanced and balanced data and outperformed the nearest mean classifier (NMC) and the independent classification rule (ICR). The study demonstrated that
Volatile-Oils
发表于 2025-3-29 18:56:44
http://reply.papertrans.cn/48/4701/470030/470030_47.png
半圆凿
发表于 2025-3-29 21:45:47
http://reply.papertrans.cn/48/4701/470030/470030_48.png
失望昨天
发表于 2025-3-30 02:00:31
Arthur Marzinkowski,Salem Benferhat,Anastasia Paparrizou,Cédric Piette
立即
发表于 2025-3-30 06:42:43
http://reply.papertrans.cn/48/4701/470030/470030_50.png