LEARNING AND EXTRACTING INITIAL MEALY AUTOMATA WITH A MODULAR NEURAL-NETWORK MODEL
LEARNING AND EXTRACTING INITIAL MEALY AUTOMATA WITH A MODULAR NEURAL-NETWORK MODEL
复制标题
DOI：
10.1162/neco.1995.7.4.822
复制
发表时间：
1995-07-01
影响因子：
2.9
通讯作者：
SAJDA, J
中科院分区：
文献类型：
--
作者：
TINO, P;SAJDA, J
混合循环神经网络被证明可以从正训练样本中学习小型初始机器（可以被视为将输入字符串翻译为相应输出字符串的翻译机器，而不是将字符串分类为语法或非语法的识别自动机）。然后，再次向训练有素的神经网络（1）提供训练集，并使用具有神经元“星”拓扑的 Kohonen 自组织图将循环网络状态空间量化为代表正在学习的粉状机器的相应状态的不同区域。这使我们能够从经过训练的循环网络中提取学习到的粉状机器。一个神经网络（Kohonen 自组织映射）用于从另一个网络（循环神经网络）中提取有意义的信息。
A hybrid recurrent neural network is shown to learn small initial mealy machines (that can be thought of as translation machines translating input strings to corresponding output strings, as opposed to recognition automata that classify strings as either grammatical or nongrammatical) from positive training samples. A well-trained neural net(1) is then presented once again with the training set and a Kohonen self-organizing map with the ''star'' topology of neurons is used to quantize recurrent network state space into distinct regions representing corresponding states of a mealy machine being learned. This enables us to extract the learned mealy machine from the trained recurrent network. One neural network (Kohonen self-organizing map) is used to extract meaningful information from another network (recurrent neural network).