会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 10. 发明授权
    • Unsupervised neural network classification with back propagation
    • 无监督神经网络分类与反向传播
    • US5590218A
    • 1996-12-31
    • US481108
    • 1995-06-07
    • Leonard Ornstein
    • Leonard Ornstein
    • G06N3/08G06K9/62
    • G06K9/6267G06N3/088Y10S128/925
    • An unsupervised back propagation method for training neural networks. For a set of inputs, target outputs are assigned l's and O's randomly or arbitrarily for a small number of outputs. The learning process is initiated and the convergence of outputs towards targets is monitored. At intervals, the learning is paused, and the values for those targets for the outputs which are converging at a less than average rate, are changed (e.g., 0.fwdarw.1, or 1.fwdarw.0), and the learning is then resumed with the new targets. The process is continuously iterated and the outputs converge on a stable classification, thereby providing unsupervised back propagation. In a further embodiment, samples classified with the trained network may serve as the training sets for additional subdivisions to grow additional layers of a hierarchical classification tree which converges to indivisible branch tips. After training is completed, such a tree may be used to classify new unlabelled samples with high efficiency. In yet another embodiment, the unsupervised back propagation method of the present invention may be adapted to classify fuzzy sets.
    • 一种用于训练神经网络的无监督反向传播方法。 对于一组输入,对于少量输出,目标输出被随机或任意地分配l和o。 开始学习过程,监测产出对目标的趋同。 每隔一段时间,学习被暂停,并且以小于平均速率收敛的输出的那些目标的值被改变(例如,0-> 1或1-> 0),并且然后恢复学习 与新的目标。 该过程不断迭代,输出收敛于稳定的分类,从而提供无监督的反向传播。 在进一步的实施例中,被分类为经过训练的网络的样本可以用作用于附加细分的训练集,以生长收敛到不可分支分支提示的分层分类树的附加层。 训练完成后,可以使用这样一棵树来高效地分类新的未标记的样品。 在另一个实施例中,本发明的无监督反向传播方法可以适于对模糊集进行分类。