?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=Modelling+Learning+as+Modelling&rft.creator=Moss%2C+Scott&rft.creator=Edmonds%2C+Bruce&rft.subject=Artificial+Intelligence&rft.subject=Machine+Learning&rft.subject=Philosophy+of+Science&rft.subject=Social+Psychology&rft.description=Economists+tend+to+represent+learning+as+a+procedure+for+estimating+the+parameters+of+the+%22correct%22+econometric+model.+We+extend+this+approach+by+assuming+that+agents+specify+as+well+as+estimate+models.+Learning+thus+takes+the+form+of+a+dynamic+process+of+developing+models+using+an+internal+language+of+representation+where+expectations+are+formed+by+forecasting+with+the+best+current+model.+This+introduces+a+distinction+between+the+form+and+content+of+the+internal+models+which+is+particularly+relevant+for+boundedly+rational+agents.+We+propose+a+framework+for+such+model+development+which+use+a+combination+of+measures%3A+the+error+with+respect+to+past+data%2C+the+complexity+of+the+model%2C+the+cost+of+finding+the+model+and+a+measure+of+the+model's+specificity+The+agent+has+to+make+various+trade-offs+between+them.+A+utility+learning+agent+is+given+as+an+example.&rft.date=1994-11&rft.type=Journal+(Paginated)&rft.type=PeerReviewed&rft.format=application%2Fpostscript&rft.identifier=http%3A%2F%2Fcogprints.org%2F510%2F1%2FlearningA4.ps&rft.format=application%2Fpdf&rft.identifier=http%3A%2F%2Fcogprints.org%2F510%2F5%2Flearning.pdf&rft.identifier=++Moss%2C+Scott+and+Edmonds%2C+Bruce++(1994)+Modelling+Learning+as+Modelling.++%5BJournal+(Paginated)%5D+++++&rft.relation=http%3A%2F%2Fcogprints.org%2F510%2F