Expert Systems - Computer Science Department - Montana State 专家系统-计算机科学系,蒙大纳州-PPT精品ppt课件.ppt

Expert Systems - Computer Science Department - Montana State 专家系统-计算机科学系,蒙大纳州-PPT精品ppt课件.ppt

ID:59419797

大小:118.00 KB

页数:32页

时间:2020-09-19

Expert Systems - Computer Science Department - Montana State 专家系统-计算机科学系,蒙大纳州-PPT精品ppt课件.ppt_第1页
Expert Systems - Computer Science Department - Montana State 专家系统-计算机科学系,蒙大纳州-PPT精品ppt课件.ppt_第2页
Expert Systems - Computer Science Department - Montana State 专家系统-计算机科学系,蒙大纳州-PPT精品ppt课件.ppt_第3页
Expert Systems - Computer Science Department - Montana State 专家系统-计算机科学系,蒙大纳州-PPT精品ppt课件.ppt_第4页
Expert Systems - Computer Science Department - Montana State 专家系统-计算机科学系,蒙大纳州-PPT精品ppt课件.ppt_第5页
资源描述:

《Expert Systems - Computer Science Department - Montana State 专家系统-计算机科学系,蒙大纳州-PPT精品ppt课件.ppt》由会员上传分享,免费在线阅读,更多相关内容在教育资源-天天文库

1、ExpertSystemsandTheirApplicationsJohnPaxtonMontanaStateUniversityAugust14,2019BozemanDefinitionsAmodelandassociatedprocedurethatexhibits,withinaspecificdomain,adegreeofexpertiseinproblemsolvingthatiscomparabletothatofahumanexpert.(Ignizio)Anexpertsystemisacomputersystemwhich

2、emulatesthedecision-makingabilityofahumanexpert.(Giarratono)CharacteristicsOperatesinanarrowdomainSeparatesknowledgefromprocessingCanexplainhowaparticularconclusionisreachedCanexplainwhyspecificdataisneededPermitsinexactreasoningCanmakemistakesChangesareeasytoincorporateComp

3、onentsProgram=Algorithm+DataStructureExpertSystem=InferenceEngine+KnowledgeUsage(2019)AreaPercentageProduction/OpsMgmt48%Finance17%InformationSystems12%Marketing/Transactions10%Accounting/Auditing6%InternationalBusiness3%HumanResources2%Other2%WhyUseanExpertSystem?Helpsprese

4、rveknowledge--buildsupthecorporatememoryofthefirm.Helpsifexpertiseisscarce,expensive,orunavailable.Helpsifundertimeandpressureconstraints.Helpsintrainingnewemployees.Helpsimproveworkerproductivity.ArchitectureUSERINTERFACEKNOWLEDGEBASEINFERENCE ENGINEWORKING MEMORYKnowledgeB

5、aseContainsfactsantacid(Imodium)Containsrulesiftraveler(x)andstomach-pains(x) thentake(y,antacid(y))InferenceEngineRulesthatmatchworkingmemoryareidentifiedandthenfired.Thisupdatesworkingmemoryandtheknowledgebase.Theprocessisrepeated.InferenceEngineConflictResolutionfireallma

6、tchingrulesfirethefirstmatchingrulefirethehighestprioritymatchingrulefirethemostspecificrulefiretherulethatusesthemostrecentdataInferenceEngineForwardChaining.Startingwiththedata,aconclusionisreached. cat(Mulder) cat(x)mammal(x)BackwardChaining.Startingwithahypothesis,itwo

7、rksbackwardstothedata.UncertaintySourcesWeakimplicationsImpreciselanguage(e.g.“often”)UnknowndataCombiningviewsofdifferentexpertsUncertaintyCertaintyFactors.Dempster-ShaferTheory.BayesianNetworks.FuzzyLogic.CertaintyFactorsIFthelightisgreen THENitisoktocrossthestreet cf=0.9+

8、easytocompute+easytopropagate-somewhatadhoc-allcertaintyfactorsareindepende

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。