irani@cs.umn.edu (Erach Irani) (07/18/90)
I agree, neural nets are the latest trick and people are using them where older techniques do better. This is good if people do comparisons with the older techniques, but not many people know about the older techniques INITIALLY (until reviewers, co-workers ask for a comparison). And so once they learn about the older techniques they can push the new techniques (like neural nets) into newer applications (if possible) or show how they do better/worse on older applications (as compared to older techniques). Presumably, it will take time but new applications will be found where older techniques were not as good once researchers knowing new techniques learn the older ones once researchers knowing the older techniiques will bring the researchers with newer techniques into contact with the older techniques (which I already see happenning with neural nets). - erach -- Phone : (Home) (612) 378-2336 Work : (612) 627-4850 InterNet : irani@cs.umn.edu UUCP: uunet!umn-cs!irani Postal Address: Erach A.Irani; 1717, Rollins Ave.; Minneapolis, MN 55414.
reynolds@cochlea.bu.edu (John Reynolds) (07/18/90)
>>>>> On 18 Jul 90 16:04:59 GMT, irani@cs.umn.edu (Erach Irani) said: In article <1990Jul18.160459.18705@cs.umn.edu> irani@cs.umn.edu (Erach Irani) writes: Erach> Presumably, it will take time but new applications will be found where Erach> older techniques were not as good once researchers knowing new techniques Erach> learn the older ones once researchers knowing the older techniiques will Erach> bring the researchers with newer techniques into contact with the older Erach> techniques (which I already see happenning with neural nets). You know I know you meant to give us the impression that we should understand this but can't!