计算机工程与应用
計算機工程與應用
계산궤공정여응용
COMPUTER ENGINEERING AND APPLICATIONS
2014年
16期
62-66
,共5页
神经网络%序列神经元%序列神经网络%算法设计
神經網絡%序列神經元%序列神經網絡%算法設計
신경망락%서렬신경원%서렬신경망락%산법설계
neural networks%sequence neuron%sequence neural networks%algorithm design
为提高神经网络的逼近能力,提出一种基于序列输入的神经网络模型及算法。模型隐层为序列神经元,输出层为普通神经元。输入为多维离散序列,输出为普通实值向量。先将各维离散输入序列值按序逐点加权映射,再将这些映射结果加权聚合之后映射为隐层序列神经元的输出,最后计算网络输出。采用Levenberg-Marquardt算法设计了该模型学习算法。仿真结果表明,当输入节点和序列长度比较接近时,模型的逼近能力明显优于普通神经网络。
為提高神經網絡的逼近能力,提齣一種基于序列輸入的神經網絡模型及算法。模型隱層為序列神經元,輸齣層為普通神經元。輸入為多維離散序列,輸齣為普通實值嚮量。先將各維離散輸入序列值按序逐點加權映射,再將這些映射結果加權聚閤之後映射為隱層序列神經元的輸齣,最後計算網絡輸齣。採用Levenberg-Marquardt算法設計瞭該模型學習算法。倣真結果錶明,噹輸入節點和序列長度比較接近時,模型的逼近能力明顯優于普通神經網絡。
위제고신경망락적핍근능력,제출일충기우서렬수입적신경망락모형급산법。모형은층위서렬신경원,수출층위보통신경원。수입위다유리산서렬,수출위보통실치향량。선장각유리산수입서렬치안서축점가권영사,재장저사영사결과가권취합지후영사위은층서렬신경원적수출,최후계산망락수출。채용Levenberg-Marquardt산법설계료해모형학습산법。방진결과표명,당수입절점화서렬장도비교접근시,모형적핍근능력명현우우보통신경망락。
To enhance the approximation capability of neural networks, a sequence input-based neural networks model, whose input of each dimension is a discrete sequence, is proposed. This model concludes three layers, in which the hidden layer consists of sequence neurons, and the output layer consists of common neurons. The inputs are multi-dimensional discrete sequences, and the outputs are common real value vectors. The discrete values in input sequence are in turn weighted and mapped, and then these mapping results are weighted and mapped for the output of sequence neurons in hidden layer, the networks outputs are obtained. The learning algorithm is designed by employing the Levenberg-Marquardt algo-rithm. The simulation results show that, when the number of the input nodes is relatively close to the length of the sequence, the proposed model is obviously superior to the common artificial neural networks.