Wilson Robert C
Department of Bioengineering, University of Pennsylvania, Philadelphia, PA 19103, USA.
Neural Comput. 2009 Mar;21(3):831-50. doi: 10.1162/neco.2008.03-07-496.
We introduce a novel type of neural network, termed the parallel Hopfield network, that can simultaneously effect the dynamics of many different, independent Hopfield networks in parallel in the same piece of neural hardware. Numerically we find that under certain conditions, each Hopfield subnetwork has a finite memory capacity approaching that of the equivalent isolated attractor network, while a simple signal-to-noise analysis sheds qualitative, and some quantitative, insight into the workings (and failures) of the system.
我们引入了一种新型神经网络，称为并行霍普菲尔德网络，它能够在同一神经硬件中同时并行地影响许多不同的、独立的霍普菲尔德网络的动力学。通过数值计算我们发现，在某些条件下，每个霍普菲尔德子网络都具有有限的存储容量，接近等效孤立吸引子网络的存储容量，而简单的信噪比分析为系统的运行（和故障）提供了定性以及一些定量的见解。
