Fixing
the inference rules seems to be OK, based on my experience with Novamente's PTL
inference system. And fixing the overall inference control strategy
seems to be OK. But context-specific inference control schemata (working
within this overall framework) need to be learned, IMO, otherwise real-world
inference cannot tractably work...
ben
-----Original Message-----
From: [EMAIL PROTECTED] [mailto:[EMAIL PROTECTED]On Behalf Of Yan King Yin
Sent: Monday, September 12, 2005 1:01 PM
To: agi@v2.listbox.com
Subject: Re: [agi] Knowledge and learning.Real Machine Learning is the deductions-inferences that can be drawn from
machine known knowledge by the AI programs. Here lies the true learning to
learn. Rather than the acquisition of known knowledge.Yes, I think the central issue is how an AGI can derive higher-level knowledge from existing knowledge or experience. For example, from seeing 10 red apples and concluding that all apples are red. We should enumerate all the "inference rules" whereby new knowledge can be generated from existing knowledge.
The inference rules can be fixed. What is flexible is the set of knowledge in the AGI. This set can get increasingly abstract as the AGI repeatedly derive new knowledge from the existing base.yky
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
To unsubscribe, change your address, or temporarily deactivate your subscription, please go to http://v2.listbox.com/member/[EMAIL PROTECTED]
