Lee B W, Sheu B J
Samsung Electron. Co., Kyunggi-Do.
IEEE Trans Neural Netw. 1991;2(1):137-42. doi: 10.1109/72.80300.
Due to the rugged energy function of the original Hopfield networks, the output is usually one local minimum in the energy function. An analysis on the locations of local minima in Hopfield networks is presented, and a modified network architecture to eliminate such local minima is described. In particular, another amplifier is introduced at the processor nodes to give correction terms. This modified Hopfield network has been successfully applied to the construction of analog-to-digital converters with optimal solutions. Experimental results on the voltage transfer characteristics of data converters are presented.
由于原始霍普菲尔德网络的能量函数崎岖不平，其输出通常是能量函数中的一个局部最小值。本文对霍普菲尔德网络中局部最小值的位置进行了分析，并描述了一种用于消除此类局部最小值的改进网络架构。具体而言，在处理器节点处引入了另一个放大器以给出校正项。这种改进的霍普菲尔德网络已成功应用于具有最优解的模数转换器的构建。文中给出了数据转换器电压传输特性的实验结果。
