it isn’t clear to me on that page if they are claiming that TPUs > GPUs for training.. seems to be used when running the models
Google has started using Tensor Processing Units (TPUs) for Deep Learning models, faster & more efficient than GPUs:https://cloudplatform.googleblog.com/2016/05/Google-supercharges-machine-learning-tasks-with-custom-chip.html …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
.
@fchollet saw this on HN. Any thoughts you could share?Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
have you had a chance to give Keras a spin on one of those?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
meet the Tensor Processing Unit,
@Google's custom Deep Learning ASIC h/t@fchollet https://cloudplatform.googleblog.com/2016/05/Google-supercharges-machine-learning-tasks-with-custom-chip.html …pic.twitter.com/X9BXPs8okf
-
holy crap this is the hardware behind Skynet
End of conversation
New conversation -
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.