almost always agree w @you fchollet but don’t see why you think either driving approach here will succeed on its own, nor why symbolic systems necessarily need to be mostly handcrafted. please explain...https://twitter.com/fchollet/status/1003440490472075264 …
1) I say at the end of the thread that the successful approach (currently and for the foreseeable future) consists of systems that blend symbolic world models with deep learning perception modules. The core of such systems is symbolic though, the ML is peripheral.
-
-
2) Symbolic cognitive systems (and most software in general) doesn't *have* to be handcrafted. In the future most software will be generated. When our ML algorithms start getting good at abstraction. For now, our models just aren't conducive to abstraction.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Maybe last sentence needs rephrasing. Symbolic logic provides the task coordination but the core perception is ML. At its core it is ML and not peripheral.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Yes yes yes a million times yes. This is what we architected in our Project Intu (now open source):https://www.dropbox.com/sh/ni6f8uehxvhz9jl/AAB3NikjeidrnstvlR5iBbyja?dl=0 …
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.