• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Chinese Journal of Electronics >DropConnect Regularization Method with Sparsity Constraint for Neural Networks
【24h】

DropConnect Regularization Method with Sparsity Constraint for Neural Networks

机译：具有稀疏约束的神经网络DropConnect正则化方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

DropConnect is a recently introduced algorithm to prevent the co-adaptation of feature detectors. Compared to Dropout, DropConnect gains state-of-the-art results on several image recognition benchmarks. Motivated by the success of DropConnect, we extended this algorithm with the ability of sparse feature selection. In DropConnect algorithm, the dropping masks of weights are generated using Bernoulli gating variables that are independent of the weights and activations. We introduce a new strategy to generate masks depending on the outputs of previous layer. Using this method, neurons which are promising to produce sparser features will be assigned a bigger possibility to keep active in the forward and backward propagations. We then evaluate such sparsity constrained DropConnect on MNIST and CIFAR datasets in comparison with ordinary DropConnect and Dropout method. The results show that our new method improves the sparsity of features significantly, while not degrading the precision.
机译：DropConnect是最近引入的一种算法，用于防止特征检测器的共同适应。与Dropout相比，DropConnect在多个图像识别基准上获得了最新的结果。受DropConnect成功的推动，我们通过稀疏特征选择功能扩展了该算法。在DropConnect算法中，使用独立于权重和激活的Bernoulli门控变量生成权重的下降掩码。我们介绍了一种根据上一层的输出生成蒙版的新策略。使用这种方法，有望产生稀疏特征的神经元将被赋予更大的可能性，使其在向前和向后传播中保持活跃。然后，与普通的DropConnect和Dropout方法相比，我们在MNIST和CIFAR数据集上评估了这种稀疏性受限的DropConnect。结果表明，我们的新方法在不降低精度的情况下显着提高了特征的稀疏性。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号