paper-with-me

Papers

Guided Dropout

2018-12-10 · Rohit Keshari, Richa Singh, Mayank Vatsa

Dropout is often used in deep neural networks to prevent over-fitting. Conventionally, dropout training invokes \textit{random drop} of nodes from the hidden layers of a Neural Network. It is our hypothesis that a guided selection of nodes for intelligent dropout can lead to better generalization as compared to the traditional dropout. In this research, we propose "guided dropout" for training deep neural network which drop nodes by measuring the strength of each node. We also demonstrate that conventional dropout is a specific case of the proposed guided dropout. Experimental evaluation on multiple datasets including MNIST, CIFAR10, CIFAR100, SVHN, and Tiny ImageNet demonstrate the efficacy of the proposed guided dropout.

📄 PDF Abstract BibTeX arXiv:1812.03965

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

From Uncertainty to Trust: Enhancing Reliability in Vision-Language Models with Uncertainty-Guided Dropout Decoding

2024-12-09 · Yixiong Fang, Ziran Yang, Zhaorun Chen, Zhuokai Zhao 외

Large vision-language models (LVLMs) demonstrate remarkable capabilities in multimodal tasks but are prone to misinterpreting visual inputs, often resulting in hallucinations and unreliable outputs. To address these chal…

Fast Power system security analysis with Guided Dropout

2018-01-30 · Benjamin Donnot, Isabelle Guyon, Marc Schoenauer, Antoine Marot 외

We propose a new method to efficiently compute load-flows (the steady-state of the power-grid for given productions, consumptions and grid topology), substituting conventional simulators based on differential equation so…

Adversarial Dropout for Recurrent Neural Networks

2019-04-22 · Sungrae Park, Kyungwoo Song, Mingi Ji, Wonsung Lee 외

Successful application processing sequential data, such as text and speech, requires an improved generalization performance of recurrent neural networks (RNNs). Dropout techniques for RNNs were introduced to respond to t…

Language ModelingLanguage ModellingSemi-Supervised Text ClassificationText Classification

Deep learning-guided weighted averaging for signal dropout compensation in diffusion-weighted imaging of the liver

2022-02-20 · Fasil Gadjimuradov, Thomas Benkert, Marcel Dominik Nickel, Tobit Führes 외

Purpose: To develop an algorithm for the retrospective correction of signal dropout artifacts in abdominal diffusion-weighted imaging (DWI) resulting from cardiac motion. Methods: Given a set of image repetitions for a s…

Excitation Dropout: Encouraging Plasticity in Deep Neural Networks

2018-05-23 · Andrea Zunino, Sarah Adel Bargal, Pietro Morerio, Jianming Zhang 외

We propose a guided dropout regularizer for deep networks based on the evidence of a network prediction defined as the firing of neurons in specific paths. In this work, we utilize the evidence at each neuron to determin…

Decision MakingVideo Recognition