.png){kind=icon}
返回
Flipover outperforms dropout in deep learning
.png){kind=icon}
OA
AI
DOI：10.1186/s42492-024-00153-y.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Flipover, an enhanced dropout technique, is introduced to improve the robustness of artificial neural networks. In contrast to dropout, which involves randomly removing certain neurons and their connections, flipover randomly selects neurons and reverts their outputs using a negative multiplier during training. This approach offers stronger regularization than conventional dropout, refining model performance by (1) mitigating overfitting, matching or even exceeding the efficacy of dropout; (2) amplifying robustness to noise; and (3) enhancing resilience against adversarial attacks. Extensive experiments across various neural networks affirm the effectiveness of flipover in deep learning.
Keyword:
Model robustness
Regularization
Flipover
Dropout
Adversarial defense
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
6
论文数:
181
被引数:
702
机构
引用论文
Dietary Supplements from Medicinal Mushrooms: How We Are Going to Ensure Their Quality and Safety药用真菌膳食补充剂：我们如何确保其质量和安全OAAI
OAAI分享收藏分享收藏Advances in Adversarial Attacks and Defenses in Computer Vision: A Survey计算机视觉中对抗性攻击和防御的进展: 综述.png)
IEEE ACCESS
OAAI
IEEE ACCESSIF3.6
OAAI分享收藏Welding characteristics of aluminum, copper, nickel and aluminum alloy with alumina coating using ultrasonic complex vibration welding equipments铝、铜、镍及铝合金氧化铝涂层超声复合振动焊接特性研究
PREAI
分享收藏Development and evaluation of FLEMOps – a new Flood Loss Estimation MOdel for the private sectorOAAI
OAAI分享收藏Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用PROCEEDINGS OF THE IEEE
PROCEEDINGS OF THE IEEEIF25.9
PREAI
分享收藏Hypoglycemic treatments and the fibrinolytic system in maturity-onset diabetes mellitus without thromboembolic manifestations成人发病型糖尿病无血栓栓塞表现下的降糖治疗与纤溶系统
PREAI
分享收藏
查看更多内容