1. Home
2. Premium
3. IEEE ICASSP 2020 Virtual Conference May 2020
4. Corrdrop: Correlation Based Dropout For Convolutional Neural Networks

Corrdrop: Correlation Based Dropout For Convolutional Neural Networks

Collection:

IEEE ICASSP 2020 Virtual Conference May 2020

Convolutional neural networks (CNNs) can be easily over-fitted when they are over-parametered. The popular dropout that drops feature units randomly can't always work well for CNNs, due to the problem of under-dropping. To eliminate this problem, some str

• IEEE MemberUS $11.00
• Society MemberUS $0.00
• IEEE Student MemberUS $11.00
• Non-IEEE MemberUS $15.00

Purchase

Videos in this product

Corrdrop: Correlation Based Dropout For Convolutional Neural Networks

00:12:06

0 views

Convolutional neural networks (CNNs) can be easily over-fitted when they are over-parametered. The popular dropout that drops feature units randomly can't always work well for CNNs, due to the problem of under-dropping. To eliminate this problem, some str