首页> 外文会议>International Conference on Artificial Neural Networks >Post-synaptic Potential Regularization Has Potential
【24h】

Post-synaptic Potential Regularization Has Potential

机译:突触后电位正则化具有电位

获取原文

摘要

Improving generalization is one of the main challenges for training deep neural networks on classification tasks. In particular, a number of techniques have been proposed, aiming to boost the performance on unseen data: from standard data augmentation techniques to the ℓ_2 regularization, dropout, batch normalization, entropy-driven SGD and many more. In this work we propose an elegant, simple and principled approach: post-synaptic potential regularization (PSP). We tested this regularization on a number of different state-of-the-art scenarios. Empirical results show that PSP achieves a classification error comparable to more sophisticated learning strategies in the MNIST scenario, while improves the generalization compared to ℓ_2 regularization in deep architectures trained on CIFAR-10.
机译:改进泛化是在分类任务上训练深度神经网络的主要挑战之一。尤其是,已经提出了许多技术,旨在提高看不见数据的性能:从标准数据增强技术到ℓ_2正则化,辍学,批处理归一化,熵驱动的SGD等。在这项工作中,我们提出了一种优雅,简单且原则性的方法:突触后电位正则化(PSP)。我们在许多不同的最新方案中测试了这种正则化。实验结果表明,在MNIST场景中,PSP实现的分类错误可与更复杂的学习策略相提并论,而与在CIFAR-10上训练的深度架构中的ℓ_2正则化相比,PSP的泛化能力得到了提高。

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