Symbol Grounding Using Neural Networks.

机译：使用神经网络进行符号接地。

获取原文

获取原文并翻译 | 示例

页面导航

摘要
著录项
相似文献
相关主题

摘要

The classical approach to artificial intelligence (i.e. symbol manipulation) and the connectionist approach (artificial neural networks) have been criticized for their inadequacies. The philosopher John Searle's Chinese room thought experiment argued that symbolic systems have no understanding of the meaning contained in their representations. The philosophers Jerry Fodor and Zenon Pylyshyn argued that artificial neural networks could not exhibit certain features of human cognition, such as systematicity and composition of representations. We take the view that both of these problems can be solved by a suitable integration of connectionist and symbolic systems. In this work we investigate methods of using artificial neural networks to produce descriptions in propositional and predicate logic. Artificial neural networks are stuctured such that, upon training, simple features of the network correspond directly to either propositional variables in one case, and objects and predicates in the other. In both cases, the methods were tested on character recognition tasks.

机译：人工智能的经典方法（即符号操作）和连接主义方法（人工神经网络）因其不足之处而受到批评。哲学家约翰·塞尔（John Searle）的中国房间思想实验认为，符号系统对它们表示中的含义不了解。哲学家杰里·福多（Jerry Fodor）和泽农·皮利申（Zenon Pylyshyn）认为，人工神经网络无法展现人类认知的某些特征，例如系统性和表征的组成。我们认为，可以通过将连接主义和符号系统进行适当的集成来解决这两个问题。在这项工作中，我们研究了使用人工神经网络在命题和谓词逻辑中产生描述的方法。人工神经网络的结构使得在训练时，网络的简单特征在一种情况下直接对应于命题变量，而在另一种情况下对应于宾语和谓语。在这两种情况下，都对字符识别任务进行了测试。

著录项

作者
Horvitz, Richard.;
展开▼
作者单位

University of Cincinnati.;

展开▼
授予单位 University of Cincinnati.;
学科 Artificial Intelligence.;Computer Science.
学位 Ph.D.
年度 2012
页码 126 p.
总页数 126
原文格式 PDF
正文语种 eng
中图分类
关键词

相似文献

外文文献
中文文献
专利

1. The Symbol Grounding Problem Revisited: A Thorough Evaluation of the ANS Mapping Account and the Proposal of an Alternative Account Based on Symbola??Symbol Associations [J] . Bert Reynvoet, Delphine Sasanguie Frontiers in Psychology . 2016,第4期

机译：再次探讨符号基础问题：对ANS映射帐户的全面评估和基于Symbola ?? Symbol关联的替代帐户的建议
2. Symbol manipulation and rule learning in spiking neuronal networks. [J] . Fernando C Journal of Theoretical Biology . 2011,第1期

机译：尖刺神经网络中的符号操纵和规则学习。
3. Symbol Grounding Association in Multimodal Sequences with Missing Elements [J] . Raue Federico, Dengel Andreas, Breuel Thomas M., The Journal of Artificial Intelligence Research . 2018,第期

机译：符号与缺失元素的多模式序列的接地关联
4. Symbol grounding transfer with hybrid self-organizing/supervised neural networks [C] . Riga, T., Cangelosi, . 2004

机译：混合自组织/监督神经网络的符号接地转移
5. Hybrid neural networks: Using artificial neural networks for the analysis and control of biological neural networks. [D] . Chiu, Alan Wing Lun. 2002

机译：混合神经网络：使用人工神经网络来分析和控制生物神经网络。
6. The Symbol Grounding Problem Revisited: A Thorough Evaluation of the ANS Mapping Account and the Proposal of an Alternative Account Based on Symbol–Symbol Associations [O] . Bert Reynvoet, Delphine Sasanguie -1

机译：再次探讨符号基础问题：对ANS映射帐户的全面评估以及基于符号-符号关联的替代帐户的建议
7. Language acquisition and symbol grounding transfer with neural networks and cognitive robots [O] . Angelo Cangelosi, Emmanouil Hourdakis, Vadim Tikhanoff 2006

机译：使用神经网络和认知机器人进行语言习得和符号接地转移

Symbol Grounding Using Neural Networks.

摘要

著录项

相似文献

相关主题

期刊订阅