It seems many 'senior' deep learning researchers have a deep bias against the use of evolutionary computing methods. Let them eat gradients.
Old techniques get dismissed until one day they are suddenly the hot new thing. I predict reservoir computing making a comeback.
-
-
random weights also make great generative abstract artwork ( ... sometimes :-)
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
reservoir computing might work very well with unsupervised feature extraction
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Should I take out my Prolog books?
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
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.