首页> 外文会议>International conference on advances in computing, communications and informatics >A statistically resilient method of weight initialization for SFANN
【24h】

A statistically resilient method of weight initialization for SFANN

机译:SFANN重量初始化的统计上有弹性方法

获取原文

摘要

Proper weight initialization is one of the important requirements for faster training in feedforward artificial neural networks. Conventionally, these weights are initialized to small uniformly distributed random values so as to break the symmetry of weights during training, that is allow the weights to acquire different values. In this work, we have proposed a new weight initialization technique (NWIT) for sigmoidal feedforward artificial neural networks. The proposed method NWIT ensures that the output of neurons are in the active region and the range of activation function is fully utilized. The proposed routine is compared with random weight initialization method for 11 function approximation task. The proposed method NWIT is as good as if not better when compared to random weight initialization technique (RWIT).
机译:适当的重量初始化是前馈人工神经网络中更快训练的重要要求之一。传统上,这些权重被初始化为小均匀分布的随机值,以便在训练期间打破权重的对称性,这允许权重获取不同的值。在这项工作中,我们已经提出了一种新的重量初始化技术(NWIT),用于赛族型前馈人工神经网络。所提出的方法NWIT确保神经元的输出处于有源区,并且充分利用了激活功能范围。将所提出的例程与随机重量初始化方法进行比较,用于11个函数近似任务。与随机重量初始化技术(RWIT)相比,所提出的方法NWIT与如果不更好。

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