A brief history of deep learning
• The backpropagation algorithm for learning
multiple layers of non-linear features was
invented several times in the 1970’s and 1980’s
(Werbos, Amari?, Parker, LeCun, Rumelhart et. al.)
• Backprop clearly had great promise, but by the
1990’s people in machine learning had largely
given up on it because:
– It did not seem to be able to make good use
of multiple hidden layers (except in “time-
delay” and convolutional nets).
– It did not work well in recurrent networks.
评论0