Urahama K, Nagao T
Dept. of Comput. Sci. and Electron., Kyusyu Inst. of Technol., Fukuoka.
IEEE Trans Neural Netw. 1995;6(3):776-8. doi: 10.1109/72.377986.
Presents a k-winners-take-all circuit that is an extension of the winner-take-all circuit by Lazzaro et al. (1989). The problem of selecting the largest k numbers is formulated as a mathematical programming problem whose solution scheme, based on the Lagrange multiplier method, is directly implemented on an analog circuit. The wire length in this circuit grows only linearly with the number of elements, and the circuit is more suitable for real-time processing than the Hopfield networks because the present circuit produces the solution almost instantaneously-in contrast to the Hopfield network, which requires transient convergence to the solution from a precise initial state. The selection resolution in the present circuit is, however, only finite in contrast to the almost infinite resolution in the Hopfield networks.
提出了一种k胜者全得电路,它是Lazzaro等人(1989年)的胜者全得电路的扩展。选择最大的k个数的问题被表述为一个数学规划问题,其基于拉格朗日乘数法的解决方案直接在模拟电路上实现。该电路中的线长仅随元件数量线性增长,并且与霍普菲尔德网络相比,该电路更适合实时处理,因为与需要从精确初始状态瞬态收敛到解的霍普菲尔德网络不同,本电路几乎能瞬间产生解。然而,与霍普菲尔德网络中几乎无限的分辨率相比,本电路中的选择分辨率是有限的。