首页> 外文期刊>Nature >Emergence Of Complex Cell Properties By Learning To Generalize In Natural Scenes
【24h】

Emergence Of Complex Cell Properties By Learning To Generalize In Natural Scenes

机译:通过学习概括自然场景中复杂细胞特性的出现

获取原文
获取原文并翻译 | 示例
           

摘要

A fundamental function of the visual system is to encode the building blocks of natural scenes-edges, textures and shapes-that subserve visual tasks such as object recognition and scene understanding. Essential to this process is the formation of abstract representations that generalize from specific instances of visual input. A common view holds that neurons in the early visual system signal conjunctions of image features, but how these produce invariant representations is poorly understood. Here we propose that to generalize over similar images, higher-level visual neurons encode statistical variations that characterize local image regions. We present a model in which neural activity encodes the probability distribution most consistent with a given image. Trained on natural images, the model generalizes by learning a compact set of dictionary elements for image distributions typically encountered in natural scenes. Model neurons show a diverse range of properties observed in cortical cells. These results provide a new functional explanation for nonlinear effects in complex cells and offer insight into coding strategies in primary visual cortex (VI) and higher visual areas.
机译:视觉系统的基本功能是对自然场景的构造块(边缘,纹理和形状)进行编码,这些结构块可满足诸如对象识别和场景理解之类的视觉任务。此过程的关键是抽象表示的形成,这些抽象表示可从视觉输入的特定实例进行概括。普遍的观点认为,早期视觉系统中的神经元会发出图像特征的结合信号,但是人们对它们如何产生不变的表示却知之甚少。在这里,我们建议为了概括相似的图像,高级视觉神经元编码表征局部图像区域的统计变化。我们提出了一个模型,其中神经活动编码与给定图像最一致的概率分布。在自然图像上训练后,该模型通过学习一组紧凑的字典元素进行概括,以实现自然场景中通常会遇到的图像分布。模型神经元显示出在皮层细胞中观察到的各种特性。这些结果为复杂细胞中的非线性效应提供了新的功能解释,并提供了对初级视觉皮层(VI)和更高视觉区域的编码策略的深入了解。

著录项

  • 来源
    《Nature》 |2009年第7225期|p.83-86|共4页
  • 作者单位

    Computer Science Department & Center for the Neural Basis of Cognition, Carnegie Mellon University, Pittsburgh, PA 15213, USA;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);美国《生物学医学文摘》(MEDLINE);美国《化学文摘》(CA);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 自然科学总论;
  • 关键词

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