arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1801.02256q-bio.NC
收藏

快速从头形状编码:对联结主义建模的挑战

Rapid de novo shape encoding: a challenge to connectionist modeling

Ernest Greene

摘要:

神经网络(连接主义)模型被设计用于编码图像特征并为对象和形状识别提供构建块。这些模型通常要求:a)从一个神经元群体到另一个神经元群体的初始扩散连接,以及b)训练以在这些连接中带来功能变化,以便一个或多个高层神经元将选择性地响应特定形状刺激。高级模型提供平移、大小和旋转不变性。目前的话语指出,最近的工作对人类的知觉技能已经证明了立即编码的未知形状,只看到一次。此外,感知机制提供了平移、大小和旋转不变性。这一发现对联结主义模型提出了挑战,因为联结主义模型需要许多训练试验才能实现识别和不变性。

英文摘要:

Neural network (connectionist) models are designed to encode image features and provide the building blocks for object and shape recognition. These models generally call for: a) initial diffuse connections from one neuron population to another, and b) training to bring about a functional change in those connections so that one or more high-tier neurons will selectively respond to a specific shape stimulus. Advanced models provide for translation, size, and rotation invariance. The present discourse notes that recent work on human perceptual skills has demonstrated immediate encoding of unknown shapes that were seen only once. Further, the perceptual mechanism provided for translation, size, and rotation invariance. This finding represents a challenge to connectionist models that require many training trials to achieve recognition and invariance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑