You could say that modern deep learning is the product of a co-evolution process between hardware, software, and algorithms. It originally arose thanks to the availability of GPUs and CUDA. Then we started optimizing our hardware and software for these specific algos...
-
-
At this point, figuring out a different path would require a multi-year re-engineering of the entire ecosystem.
Show this threadThanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
So the current state of deep learning is at a local optimum but possibly not a global one? That sounds very fitting.
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.