Irreversible spin glasses and neural networks
Irreversible spin glasses and neural networks
复制标题
不可逆自旋玻璃和神经网络
DOI：
--
复制
发表时间：
1987
期刊：
影响因子：
--
通讯作者：
S. Solla
中科院分区：
文献类型：
--
作者：
J. Hertz;G. Grinstein;S. Solla
我们研究了当单元之间的相互作用不对称时，自旋玻璃和联想记忆网络的性质是如何改变的。我们的模型是受热噪声影响的模拟网络（Langevin模型）。在一个近似成为精确的大自旋维数的限制，我们发现，自旋玻璃相被抑制，即使是任意小的不对称性。然而，在联想网络中，记忆状态并没有严重退化;它们的临界温度只是从相应的对称模型中的值降低。使存储器的数量成为系统中单元数量的有限分数的效果也与对称情况下的效果定性相同。我们认为，非对称耦合可以使检索所需的存储状态更快，因为系统将不会被困在自旋玻璃态。
We study the way in which the properties of spin glasses and associative memory networks are changed when the interactions between the units are not symmetrical. Our models are analog networks subject to thermal noise (Langevin models). In an approximation which becomes exact in the limit of large spin dimensionality, we find that spin glass phases are suppressed, even for arbitrarily small asymmetry. However, in the associative networks, memory states are not seriously degraded; their critical temperature is simply lowered from its value in the corresponding symmetric model. The effect of making the number of memories a finite fraction of the number of units in the system is also qualitatively the same as in the symmetric case. We suggest that asymmetric couplings may make retrieval of the desired memory states faster, since the system will not get trapped in spin glass states.