计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2013年
8期
178-181
,共4页
图像复原%基函数神经网络%正交基%权值修正%权值直接确定
圖像複原%基函數神經網絡%正交基%權值脩正%權值直接確定
도상복원%기함수신경망락%정교기%권치수정%권치직접학정
image restoration%basis function neural network%orthogonal basis functions%weights-updating%weights-direct-determination
给出了基函数神经网络图像复原的模型,该神经网络模型是由三层构成的前向神经网络,以一组正交基为隐层神经元的激励函数.为了避免反复迭代权值修正的冗长BP训练过程,提出了一种权值直接确定的算法.实验结果表明,该种权值直接确定算法不仅能一步确定权值而获得更快的运算速度,而且能达到更高的精度.
給齣瞭基函數神經網絡圖像複原的模型,該神經網絡模型是由三層構成的前嚮神經網絡,以一組正交基為隱層神經元的激勵函數.為瞭避免反複迭代權值脩正的冗長BP訓練過程,提齣瞭一種權值直接確定的算法.實驗結果錶明,該種權值直接確定算法不僅能一步確定權值而穫得更快的運算速度,而且能達到更高的精度.
급출료기함수신경망락도상복원적모형,해신경망락모형시유삼층구성적전향신경망락,이일조정교기위은층신경원적격려함수.위료피면반복질대권치수정적용장BP훈련과정,제출료일충권치직접학정적산법.실험결과표명,해충권치직접학정산법불부능일보학정권치이획득경쾌적운산속도,이차능체도경고적정도.
A general model for image restoration of basis function neural network is presented, a feed-forward neural network adopts a three-layer structure, where the hidden-layer neurons are activated by a group of orthogonal basis functions. To avoid lengthy BP-training of the iterative weights-updating, weights-direct-determination algorithm is proposed. Experimental results show that the algorithm not only can determine the weight by one step, but also gains higher accuracy.
