?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Embodied+induction%3A+Learning+external+representations&rft.creator=Wexler%2C+Mark&rft.subject=Machine+Learning&rft.subject=Epistemology&rft.description=The+problem+of+inductive+learning+is+hard%2C+and--despite+much+work--no+solution+is+in+sight%2C+from+neural+networks+or+other+AI+techniques.+I+suggest+that+inductive+reasoning+may+be+grounded+in+sensorimotor+capacity.+If+an+artificial+system+to+generalize+in+ways+that+we+find+intelligent+it+should+be+appropriately+embodied.+This+is+illustrated+with+a+network-+controlled+animat+that+learns+n-parity+by+representing+intermediate+states+with+its+own+motion.+Unlike+other+general+learning+devices%2C+such+as+disembodied+networks%2C+it+learns+from+very+few+examples+and+generalizes+correctly+to+previously+unseen+cases.&rft.publisher=AAAI+Press&rft.contributor=Mataric%2C+Maja&rft.date=1996&rft.type=Conference+Paper&rft.type=NonPeerReviewed&rft.format=application%2Fpostscript&rft.identifier=http%3A%2F%2Fcogprints.org%2F515%2F1%2Ffinal.ps&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F515%2F5%2Ffinal.pdf&rft.identifier=++Wexler%2C+Mark++(1996)+Embodied+induction%3A+Learning+external+representations.++%5BConference+Paper%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F515%2F