CAJ | 학술논문

RAN(Resource Allocating Network)是一种基于径向基函数的单隐含层神经网络，开始时无隐含节点，可根据新颖性准则来决定是否增加隐含节点，故有效避免了网络结构(隐含节点个数)和初始网络参数难以选取的缺点。本文首先利用RAN得到网络的初始结构及参数，然后利用扩展的卡尔曼滤波器EKF(Extended Kalman Filter)算法对网络参数进行调整，这相当于在粗调的基础上对网络参数进行细调。该网络具有学习速度快、精确度高、结构紧凑的优点，并可进一步应用于实时系统中。
RAN(Resource Allocating Network)시일충기우경향기함수적단은함층신경망락，개시시무은함절점，가근거신영성준칙래결정시부증가은함절점，고유효피면료망락결구(은함절점개수)화초시망락삼수난이선취적결점。본문수선이용RAN득도망락적초시결구급삼수，연후이용확전적잡이만려파기EKF(Extended Kalman Filter)산법대망락삼수진행조정，저상당우재조조적기출상대망락삼수진행세조。해망락구유학습속도쾌、정학도고、결구긴주적우점，병가진일보응용우실시계통중。
RAN(Resource Allocating Network) is a single hidden layer network, its hidden units are Gaussian radial basis function. RAN starts with no hidden units and grows by allocating hidden units based on novel criterion. First, we arrive at a initial network by RAN. Second, we tuned the parameters of the neural network by EKF(Extended Kalman Filter) algorithm. The advantages of RAN include quick learning, high accuracy and compact forms. It also can be applied in real time system.