• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>IEEE International Conference on Image Processing >A hopfield recurrent neural network trained on natural images performs state-of-the-art image compression
【24h】

A hopfield recurrent neural network trained on natural images performs state-of-the-art image compression

机译：在自然图像上训练的Hopfield递归神经网络执行最新的图像压缩

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The Hopfield network is a well-known model of memory and collective processing in networks of abstract neurons, but it has been dismissed for use in signal processing because of its small pattern capacity, difficulty to train, and lack of practical applications. In the last few years, however, it has been demonstrated that exponential storage is possible for special classes of patterns and network connectivity structures. Over the same time period, advances in training large-scale networks have also appeared. Here, we train Hopfield networks on discretizations of grayscale digital photographs using a learning technique called minimum probability flow (MPF). After training, we demonstrate that these networks have exponential memory capacity, allowing them to perform state-of-the-art image compression in the high quality regime. Our findings suggest that the local structure of images is remarkably well-modeled by a binary recurrent neural network.
机译：Hopfield网络是抽象神经元网络中记忆和集体处理的众所周知的模型，但由于其模式容量小，训练困难且缺乏实际应用，因此已被拒绝用于信号处理。然而，在最近几年中，已经证明了指数存储对于特殊类型的模式和网络连接结构是可能的。在同一时期，在训练大型网络方面也出现了进步。在这里，我们使用称为最小概率流（MPF）的学习技术对灰度数字照片的离散化训练Hopfield网络。经过培训，我们证明了这些网络具有指数级的存储能力，从而使它们能够在高质量的状态下执行最新的图像压缩。我们的发现表明，图像的局部结构通过二进制递归神经网络得到了很好的建模。

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