paper-with-me

홈 › Papers

Y-Drop: A Conductance based Dropout for fully connected layers

2024-09-11 · Efthymios Georgiou, Georgios Paraskevopoulos, Alexandros Potamianos

In this work, we introduce Y-Drop, a regularization method that biases the dropout algorithm towards dropping more important neurons with higher probability. The backbone of our approach is neuron conductance, an interpretable measure of neuron importance that calculates the contribution of each neuron towards the end-to-end mapping of the network. We investigate the impact of the uniform dropout selection criterion on performance by assigning higher dropout probability to the more important units. We show that forcing the network to solve the task at hand in the absence of its important units yields a strong regularization effect. Further analysis indicates that Y-Drop yields solutions where more neurons are important, i.e have high conductance, and yields robust networks. In our experiments we show that the regularization effect of Y-Drop scales better than vanilla dropout w.r.t. the architecture size and consistently yields superior performance over multiple datasets and architecture combinations, with little tuning.

📄 PDF Abstract BibTeX arXiv:2409.09088

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Towards Dropout Training for Convolutional Neural Networks

2015-12-01 · Haibing Wu, Xiaodong Gu

Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in convolutional and pooling layers is stil…

Data Augmentation

DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks

2019-07-25 · Lin Zehui, PengFei Liu, Luyao Huang, Junkun Chen 외

Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting. As an appealing alternative to recurr…

Max-Pooling Dropout for Regularization of Convolutional Neural Networks

2015-12-04 · Haibing Wu, Xiaodong Gu

Recently, dropout has seen increasing use in deep learning. For deep convolutional neural networks, dropout is known to work well in fully-connected layers. However, its effect in pooling layers is still not clear. This …

DropBlock: A regularization method for convolutional networks

2018-10-30 · NeurIPS 2018 12 · Golnaz Ghiasi, Tsung-Yi Lin, Quoc V. Le

Deep neural networks often work well when they are over-parameterized and trained with a massive amount of noise and regularization, such as weight decay and dropout. Although dropout is widely used as a regularization t…

Image ClassificationObject Detection

Variational Dropout Sparsifies Deep Neural Networks

2017-01-19 · ICML 2017 8 · Dmitry Molchanov, Arsenii Ashukha, Dmitry Vetrov

We explore a recently proposed Variational Dropout technique that provided an elegant Bayesian interpretation to Gaussian Dropout. We extend Variational Dropout to the case when dropout rates are unbounded, propose a way…

Sparse Learning