Computer object recognition at human level, despite unconstrained image viewpoints, etc. https://plus.google.com/+JeffDean/posts/hBM5wnfpW17 …, via @michael_nielsen
-
-
@michael_nielsen My PhD student is interested in probing their representations for diffs between object and letter recognition. I suppose -
@michael_nielsen there is a python library available or another relatively easy thing to get started training a convolutional net...?
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.