Re: [agi] Can symbolic approach entirely replace NN approach?

[Boris Kazachenko]

There can be variance on any level of abstraction, be that between pixels or 
between philosopical categories. And it could be in terms of any property / 
attribute of compared elements / clusters / concepts: all these are derived by 
lower-order comparisons. None of that falls from the sky, other than pixels or 
equivalents: sensory data at the limit of resolution. The rest is aquired, what 
we need to define is the aquisition process itself: cross-comp (derivation) and 
clustering (aggregation).
------------------------------------------
Artificial General Intelligence List: AGI
Permalink: 
https://agi.topicbox.com/groups/agi/T682a307a763c1ced-M1005e5cf574256f752722a0a
Delivery options: https://agi.topicbox.com/groups/agi/subscription