https://lupinepublishers.com/material-science-journal/pdf/MAMS.MS.ID.000138.pdf

University of Michigan - Ann Arbor

The possibility of Deep Learning is enormous, but it also has a limitation which we need to understand for better utilization. 

a. The systems need 10,000+ examples to learn a concept
like cows. Humans only need a handful of examples.

b. Deep Learning cannot explain how the systems got an
answer.

c. Deep Learning lacks common sense. This makes the
systems fragile and when errors are made, the errors can be
very large.


Learn Before

Related