Symbol Grounding Using Neural Networks
| Main Author: | |
|---|---|
| Language: | English |
| Published: |
University of Cincinnati / OhioLINK
2012
|
| Subjects: | |
| Online Access: | http://rave.ohiolink.edu/etdc/view?acc_num=ucin1337887977 |
| id |
ndltd-OhioLink-oai-etd.ohiolink.edu-ucin1337887977 |
|---|---|
| record_format |
oai_dc |
| spelling |
ndltd-OhioLink-oai-etd.ohiolink.edu-ucin13378879772021-08-03T06:15:34Z Symbol Grounding Using Neural Networks Horvitz, Richard P. Computer Science symbol grounding artificial neural networks neural networks The classical approach to artificial intelligence (i.e. symbol manipulation)and the connectionist approach (artificial neural networks) have beencriticized for their inadequacies. The philosopher John Searle'sChinese room thought experiment argued that symbolic systems have nounderstanding of the meaning contained in their representations. Thephilosophers Jerry Fodor and Zenon Pylyshyn argued that artificialneural networks could not exhibit certain features of human cognition,such as systematicity and composition of representations. We take theview that both of these problems can be solved by a suitable integrationof connectionist and symbolic systems. In this work we investigate methodsof using artificial neural networks to produce descriptions in propositionaland predicate logic. Artificial neural networks are stuctured such that,upon training, simple features of the network correspond directly to eitherpropositional variables in one case, and objects and predicates in the other.In both cases, the methods were tested on character recognition tasks. 2012-10-05 English text University of Cincinnati / OhioLINK http://rave.ohiolink.edu/etdc/view?acc_num=ucin1337887977 http://rave.ohiolink.edu/etdc/view?acc_num=ucin1337887977 unrestricted This thesis or dissertation is protected by copyright: all rights reserved. It may not be copied or redistributed beyond the terms of applicable copyright laws. |
| collection |
NDLTD |
| language |
English |
| sources |
NDLTD |
| topic |
Computer Science symbol grounding artificial neural networks neural networks |
| spellingShingle |
Computer Science symbol grounding artificial neural networks neural networks Horvitz, Richard P. Symbol Grounding Using Neural Networks |
| author |
Horvitz, Richard P. |
| author_facet |
Horvitz, Richard P. |
| author_sort |
Horvitz, Richard P. |
| title |
Symbol Grounding Using Neural Networks |
| title_short |
Symbol Grounding Using Neural Networks |
| title_full |
Symbol Grounding Using Neural Networks |
| title_fullStr |
Symbol Grounding Using Neural Networks |
| title_full_unstemmed |
Symbol Grounding Using Neural Networks |
| title_sort |
symbol grounding using neural networks |
| publisher |
University of Cincinnati / OhioLINK |
| publishDate |
2012 |
| url |
http://rave.ohiolink.edu/etdc/view?acc_num=ucin1337887977 |
| work_keys_str_mv |
AT horvitzrichardp symbolgroundingusingneuralnetworks |
| _version_ |
1719433621609119744 |