首页> 外文期刊>IEEE Transactions on Neural Networks >Coarse-coded higher-order neural networks for PSRI object recognition
【24h】

Coarse-coded higher-order neural networks for PSRI object recognition

机译:用于PSRI对象识别的粗编码高阶神经网络

获取原文
获取原文并翻译 | 示例

摘要

The authors describe a coarse coding technique and present simulation results illustrating its usefulness and its limitations. Simulations show that a third-order neural network can be trained to distinguish between two objects in a 4096*4096 pixel input field independent of transformations in translation, in-plane rotation, and scale in less than ten passes through the training set. Furthermore, the authors empirically determine the limits of the coarse coding technique in the position, scale, and rotation invariant (PSRI) object recognition domain.
机译:作者描述了一种粗略的编码技术,并给出了仿真结果,说明了其有用性和局限性。仿真显示,可以训练三阶神经网络以区分4096 * 4096像素输入场中的两个对象,而与平移,平面内旋转和缩放不超过训练集的十次传递无关。此外,作者根据经验确定了粗编码技术在位置,比例和旋转不变(PSRI)对象识别领域中的局限性。

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