feed-forward neural network中文是什么意思

• 反向传输神经网络

• feed    vt. 1.给…饮食，给…东西吃；给(婴儿)喂奶。 2. ...
• forward    adv. 1.向前，前进 (opp. backward) ...
• neural network    【计算机】模拟脑神经元网络〔一种模拟人脑神经细胞的电脑系 ...
• neural network    【计算机】模拟脑神经元网络〔一种模拟人脑神经细胞的电脑系统〕。
• feed forward    向前馈送，前馈; 正向输送
• forward feed    顺流进料; 顺流送料, 顺向进料; 向前进料
• forward-feed    (录像或磁盘)向前推进
• alternating projection neural network    交替投影神经网络
• ann artificial neural network    人工神经网络
• articificial neural network    类神经网络
• artificial neural network    类神经网路; 人工神经网络
• artificial neural network (ann)    类神经网络
• artificial neural network system    人工神经元网络系统
• biological neural network    神经网络
• chaotic neural network    混沌神经网络
• cnn cellular neural network    蜂窝神经网络
• cnn computational neural network    计算的神经中枢网
• connectionist neural network    连接机制神经网络
• european neural network society    欧洲神经网络学会; 欧洲神经元网络
• fnn fuzzy neural network    模糊神经网络
• fuzzy neural network    模糊神经网络
• fuzzy-neural network    模糊神经网络
• higher order neural network    高阶神经网络
• hnn hybrid neural network    混合神经网络
• hopfield neural network    霍普菲尔德神经网络

• Feed - forward neural network based on gaussnewton - nl2sol algorithm and its application
  法的前馈神经网络及应用
• Chapter 2 focuses on weight learning and structure learning of multi - layer feed - forward neural networks
  主要研究前向神经网络的权值学习和结构学习方法。
• This paper is mainly devoted to the principle and the implemental algorithms of qualitative learning for feed - forward neural networks ( fnns )
  本文主要研究前向神经网络定性学习的原理和学习算法。
• Wavelet neural network ( wnn ) is a novel feed - forward neural network based on wavelet theory , and it possesses several excellent features
  摘要小波神经网络是建立在小波理论基础上的一种新型前馈神经网络，具有许多优良特性。
• Based on rbf neural network and perceptron neural network , a four - layer feed - forward neural network named radial basis perceptron ( rbp ) network is presented
  基于rbf网络和感知器( perceptron )网络建立一四层前馈神经网络?径向基感知器( radialbasisperceptron ， rbp )网络。
• The feed - forward neural network is provided to recognizing the currency values , which makes use of the capability to extract features automatically and the error tolerance of neural networks
  利用神经网络自动特征提取能力和容错特性，提出使用前馈神经网络对面值进行识别。
• Firstly , studied feed - forward neural network and put forward a new algorithm on bp network , called bp algorithm based on robust error function ( bparef ) , and the algorithm is proved to be effective for approaching nonlinear system
  首先研究了前馈神经网络，提出了基于鲁棒误差函数的bp神经网络的算法，并且验证了其对非线性系统逼近的有效性。
• In the last of this paper we apply our algorithms to the learning of feed - forward neural network , and get some new learning algorithms . we also give some numerical experiments to compare our algorithms with others
  最后，将得到的这些优化加速收敛方法应用到了多层前馈神经网络的学习过程，给出了加速收敛的bp算法，通过实际神经网络学习问题验证了工作的成效。
• Recently a covering method for feed - forward neural network design has been proposed by professor zhang ling . based on the sphere neighborhood model , this method transforms the design of neural classifiers to a geometrical covering problem
  近来张铃教授提出了一种前馈神经网络设计的覆盖方法，它以球面领域模型为基础，使得神经网络的设计转化为几何覆盖问题。
• To overcome the limitations of general fnns and bp algorithm , this thesis introduced a hybrid feed - forward neural network , which is composed of a linear model and a general multi - layer fnn , and proposed a new learning algorithm for the hybrid fnn
  其次，针对bp网络存在的缺陷，结合前向神经网络和线性最小二乘法的优点，构造了一种基于混合结构的神经网络，提出了相应的非迭代的快速学习算法。