【正文】 expert systems can help to represent the expertise of multiple experts when they have opposing views. ? Negnevitsky, Pearson Education, 2023 43 ? Although fuzzy systems allow expression of expert knowledge in a more natural way, they still depend on the rules extracted from the experts, and thus might be smart or dumb. Some experts can provide very clever fuzzy rules – but some just guess and may even get them wrong. Therefore, all rules must be tested and tuned, which can be a prolonged and tedious process. For example, it took Hitachi engineers several years to test and tune only 54 fuzzy rules to guide the Sendal Subway System. ? Negnevitsky, Pearson Education, 2023 44 ? In recent years, several methods based on neural work technology have been used to search numerical data for fuzzy rules. Adaptive or neural fuzzy systems can find new fuzzy rules, or change and tune existing ones based on the data provided. In other words, data in – rules out, or experience in – mon sense out. ? Negnevitsky, Pearson Education, 2023 45 Summary ? Expert, neural and fuzzy systems have now matured and been applied to a broad range of different problems, mainly in engineering, medicine, finance, business and management. ? Each technology handles the uncertainty and ambiguity of human knowledge differently, and each technology has found its place in knowledge engineering. They no longer pete。 rather they plement each other. ? Negnevitsky, Pearson Education, 2023 46 ? A synergy of expert systems with fuzzy logic and neural puting improves adaptability, robustness, faulttolerance and speed of knowledgebased systems. Besides, puting with words makes them more “human”. It is now mon practice to build intelligent systems using existing theories rather than to propose new ones, and to apply these systems to realworld problems rather than to “toy” problems. ? Negnevitsky, Pearson Education, 2023 47 P e r iodK e y Eve ntsT he bi r t h of A r t i f i ci alI nte l l i g ence( 194 3–1 956 )McC ul l oc h and P i t t s, A Lo gi cal C a l cu l us of t he I de asI m m anent i n N e rvou s Ac t i vi t y , 19 4 3T u r i ng , C om put i ng Mac hine ry a nd In t e l l i ge nce , 1 950T he E l e ct r on i c N um er i c al I nte g r at o r and C al cul at o rpro j ect (v on N eum ann)Sh annon , P rogram m i ng a C om pu t e r f o r Pla yi n g C hes s ,1950T he D ar t m outh C ol l eg e sum m er w ork shop o n m achi n ei nt el l i g ence, ar t i f i ci al n eur al n et s and aut om at a t he ory ,1956Main events in the history of AI ? Negnevitsky, Pearson Education, 2023 48 P e r iod K e y Eve n t sT he r i se o f a r t i f i c i a li nt el l i g ence( 1956 – l a t e 19 60s)LISP ( McC a r t hy )T he G ene r al Prob l em So l v er ( G PR ) pro j ec t ( N ew el l andSim on)N ew el l and S i m on, H um an P robl em S ol vi ng , 1972Mi n sk y , A F ram ew ork f or R epr ese n t i ng K now l edge , 1975T he di si l l u si o nm enti n a r t i f i ci ali nt el l i g ence ( l at e1960 s–e ar l y 1970 s)C ook , Th e C om pl ex i t y of Th eor em P rov i ng P roce dure s ,1971K a r p, R ed uci bi l i t y Am ong C om b i na t or i a l P rob l em s , 1972T he L i g ht h i l l R epo r t , 1971? Negnevitsky, Pearson Education, 2023 49 P e r iod K e y Eve ntsT he di scov er y ofexper t sy st em s ( ear l y197 0s–m i d 198 0s)D E N D R A L ( Feig enbaum , B uchanan a nd L ed er b er g ,Stanf ord U n i v er s i t y )MY C I N ( Feig enbaum and Sh or t l i f f e, S t an f o r d U niv er si t y )PR O SP E C T O R (St anfo r d R e sea r ch I nst i t u t e)PR O L O G a logi c pr ogram m i ng la ngu ag e ( C o l m er auer ,R ousse l and K ow al sk i , F r an ce)E MY C I N (St anf ord U n i v er s i t y )Wat er m an, A G uide t o E xper t S yst em s , 198 6? Negnevitsky, Pearson Education, 2023 50 P e r iod K e y Eve ntsT he re bi r t h o far t i f i c i a l neu r a l w ork s( 196 5–o nw ar d s)H opfi e l d, N e ura l N et w o rks a nd P h ysi cal Sys t em s w i t hE m ergen t C ol l ec t i ve C om pu t a t i on al Ab i l i t i e s , 198 2K oho n en, S el f O rg ani zed F o rm at i on o f To po l og i ca l l yC orrec t F ea t ur e M aps , 1 982R um el hart a nd M cC l e l l and, P a ral l e l D i s t r i bu t edP roces si n g , 198 6T he Fi r st I E E E I nte r nat i onal C onf er ence on N eu r alN et w ork s, 1987H ayk i n, N eura l N et w o rks , 199 4N eura l N et w o r k , MA T L A B A pp l i cat i on T oolb ox ( T h eMat h Wo r k , I nc.)? Negnevitsky, Pearson Education, 2023 51 P e r iod K e y Eve ntsE v olut i on ar y putat i on ( ear l y197 0s–onw ar d s)R echenb er g , E vol ut i ons st r ate gie n O p t i m i eru ngTechn i sch er Sy st em e N ach P ri n zi p i en der B i o l ogi sch enI nfo rm at i on , 19 73H oll an d, A dap t a t i on i n N a t ura l an d A rt i f i c i a l Sys t em s ,1975.K oz a, G ene t i c P rog ram m i ng : O n t he P r ogram m i n g of t heC om puter s by Mea ns o f N atu ral Se l ec t i o n , 199 2.Sch w e f e l, E v olution and O ptimum Se e k ing , 19 95Fo g el , E vol ut i ona r y C om put at i on – To w a rds a N ewP hil o soph y of Mac hin e I n t el l i gen ce , 1 995 .? Negnevitsky, Pearson Education, 2023 52 P e r iod K e y Eve n t sC om puti ng w i t hWord s( l a t e 1 980s– onw ar d s)Z adeh, F uzzy S et s , 196 5Z adeh, F uzzy A l go ri t hm s , 196 9Mam dani , A pp l i cat i on o f F uz zy Log i c t o A pp rox i m at eR eason i ng U s i ng L i ngu i s t i c Syn t hes i s , 1977Su g eno, F uzzy T heor y , 198 3Japan ese “f uz z y ” consum er produ ct s ( d i shw a she r s,w ashi ng m achi nes, ai r co ndi t i o ner s, t el ev i si on