计算机系统应用
計算機繫統應用
계산궤계통응용
APPLICATIONS OF THE COMPUTER SYSTEMS
2014年
6期
183-186
,共4页
BP神经网络%条件对数似然%多类分类器%收敛速度%监督性神经网络
BP神經網絡%條件對數似然%多類分類器%收斂速度%鑑督性神經網絡
BP신경망락%조건대수사연%다류분류기%수렴속도%감독성신경망락
BP neural network%conditional log-likelihood%multi-class classifier%convergence speed%supervisory neural network
BP 神经网络分类器存在收敛速度慢的缺陷,为了提高分类器性能,针对这一缺陷对 BP 算法进行改进。提出将条件对数似然(CLL)准则融入到监督性BP神经网络多类型分类过程中,利用CLL的可分解性优势,计算测试样本的条件概率,在误差反向传播时利用条件概率对权值进行相应的加权降权操作,简化误差反馈过程中的计算量。在实验中对改进算法的收敛速度和准确率进行了测试,说明了该算法的有效性及实用性。
BP 神經網絡分類器存在收斂速度慢的缺陷,為瞭提高分類器性能,針對這一缺陷對 BP 算法進行改進。提齣將條件對數似然(CLL)準則融入到鑑督性BP神經網絡多類型分類過程中,利用CLL的可分解性優勢,計算測試樣本的條件概率,在誤差反嚮傳播時利用條件概率對權值進行相應的加權降權操作,簡化誤差反饋過程中的計算量。在實驗中對改進算法的收斂速度和準確率進行瞭測試,說明瞭該算法的有效性及實用性。
BP 신경망락분류기존재수렴속도만적결함,위료제고분류기성능,침대저일결함대 BP 산법진행개진。제출장조건대수사연(CLL)준칙융입도감독성BP신경망락다류형분류과정중,이용CLL적가분해성우세,계산측시양본적조건개솔,재오차반향전파시이용조건개솔대권치진행상응적가권강권조작,간화오차반궤과정중적계산량。재실험중대개진산법적수렴속도화준학솔진행료측시,설명료해산법적유효성급실용성。
BP neural network classifier has a slowly convergence rate, in order to improve the performance of the classifier, there is an improvement in BP algorithm for the problem. The Conditional Log-Likelihood (CLL) is applied into the supervisory neural network classification for the multi-class selection. By using the decomposability of CLL, calculate the conditional probability of the test samples. In the error back-propagation process, increasing or reducing the corresponding weights by using the conditional probabilities, which can simplify the computation in the process of error feedback. In the paper, we test the convergence speed and accuracy for the improved algorithm in the experiment. It illustrates the effectiveness and the practicality of the algorithm.