24小时热门版块排行榜    

查看: 208  |  回复: 0
当前主题已经存档。

nnxll

金虫 (正式写手)


[资源] 【转贴】Semantic Cognition: A Parallel Distributed Processing Approach

Semantic Cognition: A Parallel Distributed Processing Approach (Bradford Books)





By Timothy T. Rogers, James L. McClelland,

Publisher:   The MIT Press
Number Of Pages:   448
Publication Date:   2006-03-01
Sales Rank:   693794
ISBN / ASIN:   0262681579
EAN:   9780262681575
Binding:   Paperback
Manufacturer:   The MIT Press
Studio:   The MIT Press


This groundbreaking monograph offers a mechanistic theory of the representation and use of semantic knowledge, integrating the strengths and overcoming many of the weaknesses of hierarchical, categorization-based approaches, similarity-based approaches, and the approach often called "theory theory." Building on earlier models by Geoffrey Hinton in the 1980s and David Rumelhart in the early 1990s, the authors propose that performance in semantic tasks arises through the propagation of graded signals in a system of interconnected processing units. The representations used in performing these tasks are patterns of activation across units, governed by weighted connections among them. Semantic knowledge is acquired through the gradual adjustment of the strengths of these connections in the course of day-to-day experience.

The authors show how a simple computational model proposed by Rumelhart exhibits a progressive differentiation of conceptual knowledge, paralleling aspects of cognitive development seen in the work of Frank Keil and Jean Mandler. The authors extend the model to address aspects of conceptual knowledge acquisition in infancy, disintegration of conceptual knowledge in dementia, "basic-level" effects and their interaction with expertise, and many findings introduced to support the idea that semantic cognition is guided by naive, domain-specific theories.



http://rapidshare.com/files/3868 ... g_Approach.rar.html

[ Last edited by laizuliang on 2007-10-31 at 16:43 ]
回复此楼
已阅   关注TA 给TA发消息 送TA红花 TA的回帖
相关版块跳转 我要订阅楼主 nnxll 的主题更新
最具人气热帖推荐 [查看全部] 作者 回/看 最后发表
[硕博家园] 读博的好处 +3 lnee 2026-08-11 3/150 2026-08-11 18:10 by 希望我好好的
[基金申请] 应该是93bebmhtak前后十一个字符比较关键 +16 Lanmanbaby 2026-08-09 26/1300 2026-08-11 17:16 by 天神眷顾
[基金申请] 分享一下我之前已中青C的计划书的filecode +3 布布和一二 2026-08-11 4/200 2026-08-11 15:20 by aasahr
[论文投稿] 职称评审,求友友推荐见刊最快的期刊 +3 工厂打螺丝 2026-08-08 3/150 2026-08-11 13:42 by 会议编辑
[基金申请] filecode +9 documentary 2026-08-10 9/450 2026-08-11 10:08 by wk7465
[基金申请] 基金中了 +15 laoda193707 2026-08-06 15/750 2026-08-11 00:11 by jiafei2190
[基金申请] 关于代码变化问题,想知道的进来 +17 且听虎啸 2026-08-07 24/1200 2026-08-10 18:35 by zhangduo2008
[基金申请] 静等基金结果 +5 gjjjzhong 2026-08-10 16/800 2026-08-10 17:19 by Tide man
[基金申请] 国自然结果 +4 Vierhys 2026-08-10 8/400 2026-08-10 15:06 by Vierhys
[基金申请] 好奇怪的filecode +4 布布和一二 2026-08-08 5/250 2026-08-10 14:20 by 冰心玉壶晴
[基金申请] 据悉今年马上要出结果了 +7 瞬息宇宙 2026-08-10 8/400 2026-08-10 12:42 by Vivilian
[基金申请] 面上项目filecode邪修 +5 西山十月 2026-08-09 7/350 2026-08-10 07:32 by 仁砚薪传
[基金申请] filecode与中标关系的预测 +5 布布和一二 2026-08-07 5/250 2026-08-09 16:15 by 袁向阳007
[基金申请] fileCode有新解读? +10 Tide man 2026-08-08 18/900 2026-08-09 12:55 by 仁砚薪传
[基金申请] 关于豆爷回答的JTJC与%2F数量 +5 yang182083 2026-08-06 7/350 2026-08-08 18:29 by zhanghaozhu
[基金申请] 国基金的申报应该改成非等额制,评价高的钱多评价低的钱少,但是增加资助率 +7 a089 2026-08-07 7/350 2026-08-08 18:05 by gltch
[基金申请] 固定端突然变了,今天 +6 archvillain 2026-08-06 10/500 2026-08-07 16:03 by 医学老男孩
[基金申请] filecode +14 等待解的谜 2026-08-06 19/950 2026-08-07 12:20 by wlwhappy
[基金申请] filecode +8 布布和一二 2026-08-06 11/550 2026-08-06 20:41 by tangpu318
[基金申请] 影响面上的因素 +8 布布和一二 2026-08-05 11/550 2026-08-06 10:41 by 宝贝虫子
信息提示
请填处理意见