权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Symbol Processing System Modeled after Brains

以大脑为模型的符号处理系统

基本信息

批准号：
15500095
负责人：
SAKURAI Akito
金额：
$ 2.37万
依托单位：
Keio University
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (C)
财政年份：
2003
资助国家：
日本
起止时间：
2003 至 2005
项目状态：
已结题

项目摘要

We have investigated a new framework of neural network learning that is composed of multiple reinforcement learning agents among which there exist multiple legitimate candidate modules. We have invented a mechanism that facilitates competitive learning among reinforcement learning agents and ascertained its validity by computer simulations.We further investigated another type of grammar acquisition by recurrent neural networks of two different types. One type of them monitors the other type and modifies itself based on the monitored observation. We found that the networks are able to learn grammatical categories and are robust against their legion.We conducted experiments of acquisition of shift-reduce parsers in which ATIS corpus in Penn TreeBank is the corpus and ILP is the fundamental learning paradigm. To alleviate drawbacks (high cost of execution time and memory requirements) of the existing learning methods, we employed grammatical categories as learning units. We invented new methods to generate rationalized negative examples based on grammatical categories and to relearn the negative examples by investigating where those examples are in fact miss-classified. We confirmed that the accuracy improved to a bit less than 90%,Finite state automata are capable enough to represent knowledge in brain but it is well-known that they are too versatile to be successfully learned. Therefore we made research on methods to approximately learn and communicate them. We have applied reinforcement learning methods and found them to be eligible. We have invented a method to prepare a large number of grammatical categories, to try to use them in communication, and to select best ones. We implemented the method in recurrent neural networks, and conducted numerical simulations. The results are promising in a sense that the original grammatical category structure is reconstructed with paying attention only to training errors (not to generalization capabilities).

我们研究了一种新的神经网络学习框架，该框架由多个强化学习代理组成，其中存在多个合法的候选模块。我们发明了一种机制，促进强化学习代理之间的竞争学习，并通过计算机模拟确定其有效性。我们进一步研究了另一种类型的语法习得两种不同类型的递归神经网络。其中一种类型监视另一种类型，并根据监视的观察结果修改自己。我们发现，网络能够学习语法类别，并对他们的军团是健壮的。我们进行了实验的收购移位归约分析器中的ATIS语料库在Penn TreeBank的语料库和ILP是基本的学习范式。为了减轻现有学习方法的缺点（执行时间成本高和内存需求高），我们采用语法类别作为学习单元。我们发明了新的方法来生成合理化的否定的例子的语法类别的基础上，并重新学习的否定的例子，调查这些例子实际上是错误的分类。结果表明，有限状态自动机的准确率提高到了90%以下。有限状态自动机能够很好地表示大脑中的知识，但由于其通用性太强，很难被成功地学习。因此，我们研究了近似学习和交流的方法。我们已经应用了强化学习方法，并发现它们是合格的。我们发明了一种方法来准备大量的语法范畴，尝试在交际中使用它们，并选择最好的。我们在递归神经网络中实现了该方法，并进行了数值模拟。结果是有希望的，在某种意义上说，原来的语法范畴结构的重建只注意训练错误（而不是泛化能力）。