神经网络中的对称性破缺。
Symmetry breaking in neural nets.
作者信息
Pessa E
机构信息
Dipartimento di Matematica, Università degli Studi di Roma La Sapienza, Italy.
出版信息
Biol Cybern. 1988;59(4-5):277-81. doi: 10.1007/BF00332916.
In this paper two well-known homogeneous models of neural nets undergoing symmetry-breaking transitions are studied in order to see if, after the transition, there is the appearance of Goldstone modes. These have been found only in an approximate way; there are indications, however, that they can play a prominent role when the tissue is subjected to external inputs, constraining it to be slaved to the characteristics of those. This circumstance should be essential in explaining how a structured net can store complex inputs and give subsequently ordered outputs.
在本文中，我们研究了神经网络中两个著名的经历对称性破缺转变的均匀模型，以探究在转变之后是否会出现戈德斯通模式。这些模式只是以近似的方式被发现；然而，有迹象表明，当组织受到外部输入时，它们可能会发挥显著作用，迫使组织从属于这些输入的特征。这种情况对于解释一个结构化网络如何能够存储复杂输入并随后给出有序输出应该是至关重要的。
Zotero 插件