首页> 外文会议>International conference on computer analysis of images and patterns >Learning Behavior Using Multiresolution Recurrent Neural Network
【24h】

Learning Behavior Using Multiresolution Recurrent Neural Network

机译:使用多分辨率反复性神经网络学习行为

获取原文

摘要

We propose the multiresolution recurreint neural network to learn behavior based on view and action. Recurrent neural network structure has the multiresolution channel to establish between the view and the action. It is difficult to learn action using only a image generally. We solve this problem by using the 3 kinds of image on the frequency. We control the multiresolution vision using Genetic Algorithm. The action sequences is acquired by the pan-tilt camera.
机译:我们提出了多分辨率的反核神经网络,以基于视图和动作学习行为。经常性的神经网络结构具有多分辨率的通道,可以在视图和动作之间建立。很难仅使用一般图像学习动作。我们通过使用频率上的3种图像来解决这个问题。我们使用遗传算法控制多分辨率视觉。通过PAN倾斜相机获取动作序列。

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