计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2001年
1期
44-47
,共4页
张德贤%申石磊%向国全%王光霞
張德賢%申石磊%嚮國全%王光霞
장덕현%신석뢰%향국전%왕광하
启发性知识%约束训练%神经网络
啟髮性知識%約束訓練%神經網絡
계발성지식%약속훈련%신경망락
基于对目前神经网络存在问题的具体分析,认为将启发性信息引入神经网络训练将是提高网络学习能力、质量以及效率的重要途径。进而讨论了启发知识的来源与种类,将启发性知识分成诱导性约束和强制性约束两类,进而建立了引入网络训练的相应策略,给出了启发性知识引入与选择的具体原则,并建立了两种基于导数关系的启发知识模型。最后建立了神经网络的具体训练算法。具体应用结果证明了所提出策略与方法的有效性。
基于對目前神經網絡存在問題的具體分析,認為將啟髮性信息引入神經網絡訓練將是提高網絡學習能力、質量以及效率的重要途徑。進而討論瞭啟髮知識的來源與種類,將啟髮性知識分成誘導性約束和彊製性約束兩類,進而建立瞭引入網絡訓練的相應策略,給齣瞭啟髮性知識引入與選擇的具體原則,併建立瞭兩種基于導數關繫的啟髮知識模型。最後建立瞭神經網絡的具體訓練算法。具體應用結果證明瞭所提齣策略與方法的有效性。
기우대목전신경망락존재문제적구체분석,인위장계발성신식인입신경망락훈련장시제고망락학습능력、질량이급효솔적중요도경。진이토론료계발지식적래원여충류,장계발성지식분성유도성약속화강제성약속량류,진이건립료인입망락훈련적상응책략,급출료계발성지식인입여선택적구체원칙,병건립료량충기우도수관계적계발지식모형。최후건립료신경망락적구체훈련산법。구체응용결과증명료소제출책략여방법적유효성。
Based on the detailed analysis of the problems in current neural network,it is considered that the utilization of heuristic knowledge in the learning of neural network would be an important approach to improve the ability,quality and efficiency of neural network learning.This paper discusses the source and classification of heuristic knowledge,and divides them into two categories:the inducing constraint and obliged constraint.Then it establishes the strategy and detailed principle of the utilization of heuristic knowledge in neural network learning.Two heuristic knowledge models based on derivative relations are also established.At the end of the paper,a detailed algorithm of neural network learning is presented.The effectiveness of the strategy represented has been proved by results of practices.