A general framework for adaptive processing of data structures
A general framework for adaptive processing of data structures
复制标题
DOI：
10.1109/72.712151
复制
发表时间：
1998-09-01
影响因子：
--
通讯作者：
Sperduti, A
中科院分区：
文献类型：
--
作者：
Frasconi, P;Gori, M;Sperduti, A
符号处理通常需要信息的结构化组织。另一方面，大多数连接主义模型假设数据是根据相对较差的结构组织的，如数组或序列。本文所描述的框架是一种尝试，以统一的自适应模型，如人工神经网络和信念网的结构化信息处理的问题。特别是，数据变量之间的关系是由有向无环图表示的，其中数值和分类值共存。本文提出的一般框架可以看作是一个扩展的递归神经网络和隐马尔可夫模型的情况下，无环图。特别是，我们研究的监督学习问题的学习转换从输入结构化空间的输出结构化空间，其中转换被假定为承认递归隐藏的状态空间表示的问题。我们引入了一种图形形式主义来表示这类自适应转换的递归网络，即，循环图，其中节点标记的变量和边缘标记的广义延迟元素，这种表示法使得它有可能将符号和subsymbolic性质的数据。通过将递归网络展开为称为编码网络的非循环图来处理结构。这样，推理和学习算法可以很容易地从人工神经网络或概率图模型的相应算法继承。
A structured organization of information is typically required by symbolic processing. On the other hand, most connectionist models assume that data are organized according to relatively poor structures, like arrays or sequences. The framework described in this paper is an attempt to unify adaptive models like artificial neural nets and belief nets for the problem of processing structured information. In particular, relations between data variables are expressed by directed acyclic graphs, where both numerical and categorical values coexist. The general framework proposed in this paper can be regarded as an extension of both recurrent neural networks and hidden Markov models to the case of acyclic graphs. In particular we study the supervised learning problem as the problem of learning transductions from an input structured space to an output structured space, where transductions are assumed to admit a recursive hidden state-space representation. We introduce a graphical formalism for representing this class of adaptive transductions by means of recursive networks, i,e,, cyclic graphs where nodes are labeled by variables and edges are labeled by generalized delay elements, This representation makes it possible to incorporate the symbolic and subsymbolic nature of data. Structures are processed by unfolding the recursive network into an acyclic graph called encoding network. In so doing, inference and learning algorithms can be easily inherited from the corresponding algorithms for artificial neural networks or probabilistic graphical model.