Tree Echo State Networks
Tree Echo State Networks
复制标题
DOI：
10.1016/j.neucom.2012.08.017
复制
发表时间：
2013-02-04
期刊：
影响因子：
6
通讯作者：
Micheli, Alessio
中科院分区：
文献类型：
--
作者：
Gallicchio, Claudio;Micheli, Alessio
在本文中，我们提出了树回声状态网络（TreeESN）模型，概括水库计算的范式树结构的数据。TreeESN利用了一个未经训练的广义递归库，在结构化领域的学习中表现出极高的效率。此外，我们强调通过纸张的其他特点的方法：首先，我们讨论了马尔可夫表征的水库动态，扩展到树域的情况下，这是隐含的收缩设置的TreeESN状态转移函数。其次，我们研究了两种类型的状态映射函数，将TreeESN的树结构状态映射到用于分类或回归任务的固定大小的特征表示。的状态映射函数的选择和马尔可夫表征的任务之间的关系的关键作用进行了分析和实验研究人工和现实世界的任务。最后，基准和现实世界的任务的实验结果表明，TreeESN的方法，尽管其效率，可以实现与国家的最先进的，虽然更复杂的，神经和内核为基础的模型树结构化数据的结果。(C)2012 Elsevier B.V.保留所有权利。
In this paper we present the Tree Echo State Network (TreeESN) model, generalizing the paradigm of Reservoir Computing to tree structured data. TreeESNs exploit an untrained generalized recursive reservoir, exhibiting extreme efficiency for learning in structured domains. In addition, we highlight through the paper other characteristics of the approach: First, we discuss the Markovian characterization of reservoir dynamics, extended to the case of tree domains, that is implied by the contractive setting of the TreeESN state transition function. Second, we study two types of state mapping functions to map the tree structured state of TreeESN into a fixed-size feature representation for classification or regression tasks. The critical role of the relation between the choice of the state mapping function and the Markovian characterization of the task is analyzed and experimentally investigated on both artificial and real-world tasks. Finally, experimental results on benchmark and real-world tasks show that the TreeESN approach, in spite of its efficiency, can achieve comparable results with state-of-theart, although more complex, neural and kernel based models for tree structured data. (C) 2012 Elsevier B.V. All rights reserved.