Back Andrew D, Chen Tianping
Windale Technologies, Brisbane, QLD 4075, Australia.
Neural Comput. 2002 Nov;14(11):2561-6. doi: 10.1162/089976602760407964.
Recently, there has been interest in the observed capabilities of some classes of neural networks with fixed weights to model multiple nonlinear dynamical systems. While this property has been observed in simulations, open questions exist as to how this property can arise. In this article, we propose a theory that provides a possible mechanism by which this multiple modeling phenomenon can occur.
最近，人们对某些具有固定权重的神经网络对多个非线性动力系统进行建模的观测能力产生了兴趣。虽然在模拟中已经观察到了这种特性，但关于这种特性是如何产生的仍存在一些悬而未决的问题。在本文中，我们提出了一种理论，该理论提供了一种可能的机制，通过这种机制可以出现这种多重建模现象。
