On Sat, Sep 20, 2008 at 8:46 AM, Matt Mahoney <[EMAIL PROTECTED]> wrote: > But if you can learn these types of patterns then with no additional effort > you can learn patterns that directly solve the problem...
This kind of reminds me of the "people think in their natural language" theory that Steven Pinker has gone to extensive effort to show is a fallacy. It may well be true that it is possible that you can solve the problem by pattern recognition of sounds or even letters, but linguists tend to disagree that this is what happens in the brain. Besides which, if you have a mechanism that can solve this problem without any sort of abstraction, will that same mechanism be able to solve analogous problems? Or do you need another mechanism? If so, how many do you need before you can solve all the analogous problems? This is why we abstract. Trent ------------------------------------------- agi Archives: https://www.listbox.com/member/archive/303/=now RSS Feed: https://www.listbox.com/member/archive/rss/303/ Modify Your Subscription: https://www.listbox.com/member/?member_id=8660244&id_secret=114414975-3c8e69 Powered by Listbox: http://www.listbox.com
