Version Spaces: A Candidate Elimination Approach to Rule Learning

An i m p o r t a n t r e s e a r c h prob lem in a r t i f i c i a l i n t e l l i g e n c e i s t h e s t u d y o f methods f o r l e a r n i n g g e n e r a l c o n c e p t s o r r u l e s f rom a se t o f t r a i n i n g i n s t a n c e s . A n approach t o t h i s p rob lem i s p r e s e n t e d wh ich i s g u a r a n t e e d t o f i n d , w i t h o u t b a c k t r a c k i n g , a l l r u l e v e r s i o n s c o n s i s t e n t w i t h a s e t o f p o s i t i v e and n e g a t i v e t r a i n i n g i n s t a n c e s . The a l g o r i t h m put f o r t h uses a r e p r e s e n t a t i o n o f t h e space o f t hose r u l e s c o n s i s t e n t w i t h t h e observed t r a i n i n g d a t a . T h i s " r u l e v e r s i o n space " i s m o d i f i e d i n response t o new t r a i n i n g i n s t a n c e s b y e l i m i n a t i n g c a n d i d a t e r u l e v e r s i o n s found t o c o n f l i c t w i t h each new i n s t a n c e . The use o f v e r s i o n spaces i s d i s c u s s e d in t h e c o n t e x t o f Meta-DENDRAL, a program wh ich l e a r n s r u l e s i n t h e domain o f c h e m i c a l s p e c t r o s c o p y . D e s c r i p t i v e t e r m s : V e r s i o n space , r u l e l e a r n i n g , c a n d i d a t e e l i m i n a t i o n , concep t f o r m a t i o n , concep t l e a r n i n g , machine l e a r n i n g , Meta-DENDRAL.