CAJ | 학술논문

针对某些对象梯度不易计算的问题，提出一种新的优化训练方法。利用水往低处流的原理对参数进行寻优，将随机初始参数根据步长生成多维空间中点的坐标形式，用实际输出和目标输出之间的差来表示以此点为球心的球的半径，将最小半径的球作为下一步寻优的中心点。此方法具有无需计算梯度，初始值随机选取，易编程，寻优快等特点。通过仿真实验，此方法成功应用在 PID 控制器、LQR 控制器和神经网络中，获取了最优参数，具有实际操作性。
침대모사대상제도불역계산적문제，제출일충신적우화훈련방법。이용수왕저처류적원리대삼수진행심우，장수궤초시삼수근거보장생성다유공간중점적좌표형식，용실제수출화목표수출지간적차래표시이차점위구심적구적반경，장최소반경적구작위하일보심우적중심점。차방법구유무수계산제도，초시치수궤선취，역편정，심우쾌등특점。통과방진실험，차방법성공응용재 PID 공제기、LQR 공제기화신경망락중，획취료최우삼수，구유실제조작성。
A neWtraining method Was proposed to solve the problem that some gradients of the objects are not easy to calculate.This method Was based on the principle of gravity optimizes parameters.Random initial parameter based on step Was set as coordinate form Which in the midpoint of the multidimensional space.The error betWeen the actual output and the target output Was set as radius.This method had advantages Which could not need to calculate the gradient and could randomly select initial value.This method Was successfully used in the PID controller,LQR controller and neural netWork.