现代电子技术
現代電子技術
현대전자기술
MODERN ELECTRONICS TECHNIQUE
2013年
15期
108-111
,共4页
神经网络%跨越连接%极速学习机%倒立摆系统
神經網絡%跨越連接%極速學習機%倒立襬繫統
신경망락%과월련접%겁속학습궤%도립파계통
neural network%span connection%extreme learning machine%inverted pendulum system
针对基于 ELM 学习算法的单隐含层前馈神经网络需要较大的网络规模、影响网络泛化能力的问题，基于新皮层内神经元的连接特点，在前馈神经网络中引入不同层神经元之间的跨越连接，构造跨越前馈神经网络。同时，基于 ELM学习算法设计适用于跨越前馈神经网络的学习算法，提高网络的学习能力。Image Segmentation 多分类问题及直线一级倒立摆系统控制的实验研究表明，该方法能够提高网络的学习能力，具有明显的优势。
針對基于 ELM 學習算法的單隱含層前饋神經網絡需要較大的網絡規模、影響網絡汎化能力的問題，基于新皮層內神經元的連接特點，在前饋神經網絡中引入不同層神經元之間的跨越連接，構造跨越前饋神經網絡。同時，基于 ELM學習算法設計適用于跨越前饋神經網絡的學習算法，提高網絡的學習能力。Image Segmentation 多分類問題及直線一級倒立襬繫統控製的實驗研究錶明，該方法能夠提高網絡的學習能力，具有明顯的優勢。
침대기우 ELM 학습산법적단은함층전궤신경망락수요교대적망락규모、영향망락범화능력적문제，기우신피층내신경원적련접특점，재전궤신경망락중인입불동층신경원지간적과월련접，구조과월전궤신경망락。동시，기우 ELM학습산법설계괄용우과월전궤신경망락적학습산법，제고망락적학습능력。Image Segmentation 다분류문제급직선일급도립파계통공제적실험연구표명，해방법능구제고망락적학습능력，구유명현적우세。
The single?hidden layer feedforward neural network(SLFN)based on ELM needs larger?scale network structure to solve practical applications,which will influence the generalization capability. In order to solve the problem,a span feedforward neural network (SFN) is proposed based on the characteristic of neocortex neurons. The span connections between any two non ? adjacent layers were introduced into this network. At the same time,an improved learning algorithm based on ELM is presented,the proposed approach of span feedforward neural network and improved ELM learning algorithm is used for some benchmark problems. The study on Image Segmentation multi?classification problem and linear 1?stage inverted pendulum system control show that the proposed approach performs better than SLFN and ELM,and it could improve the learning ability of the nerwork.
