I think it should be crystal clear that many of the connectionist tradition fervently believe that the symbolist tradition took the wrong path and therefore is not worth taking again. Fool me once, shame on you; fool me twice, shame on me. Hybrid is just a stop-gap solution.
This is a terrific graph, which highlights the historical roots of the animosity between neural nets and classical AI It also implicitly highlights fact that too few people have ever considering merging the best of the two traditions History is zero sum, when we need hybrids!https://twitter.com/intuitmachine/status/1200796873495318528 …
-
-
-
As regards “the symbolic school” vs. connectionism I never heard anything from the former against the latter. It was not the symbolic community that abandoned NNs from the mid 90s to ~2010; I was told at flagship ML conferences in the early 2000s that ANNs were “over”.
- 1 more reply
New conversation -
-
-
Right. Nature does not silo. There are specialized functions in specific cases, but generalists survive bottlenecks. Ego is the root of siloing. It is the desire the protect your kingdom. Sometimes kingdoms need to fall or be remapped to evolve. Mitochondria = Symbiotes survive.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Take a look at our manuscript on the history of knowledge graphs which goes back 50 years on the work of knowledge/logic and data. I’d appreciate your comments http://knowledgegraph.today/paper.html
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
Show additional replies, including those that may contain offensive content
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.