“An automaton designed on statistical principles, which can evolve an internal organizing routine to respond to regularities of its sensory input, is capable in principle of developing its own symbols for concepts of any order of abstraction, without prior instruction.” (1956)https://twitter.com/doristsao/status/1038881901065396224 …
-
-
I've been reading some older Norbert Weiner works... era of first principles and wide vistas
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
A lot more wrong more often. http://www-formal.stanford.edu/jmc/history/dartmouth/dartmouth.html …pic.twitter.com/xgKYCPwnPp
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
They were more into high level goals using reasoning over few items. Now we are focusing on many technicalities using an obfuscated language. Too high or too low, no middle grounds or compromise. A clear understandable theory of intelligence is needed for generalization
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Kinda makes the case for connectionism being the right path, no?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
He is basically describing a lossless file compression algorithm. The word sensory is redundant, there is just "input". Each layer of abstraction is formed by "new symbol" = pattern of older symbols, then reassign symbol identifiers by bit length = frequency of occurrence. Y/N?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.
