Issues With Recurrent Neural Networks
Most RNNs have had scaling issues. In particular, RNNs cannot be easily trained for large numbers of neuron units nor for large numbers of inputs units. Successful training has been mostly in time series problems with few inputs.
Read more about this topic: Recurrent Neural Network
Famous quotes containing the words issues, recurrent and/or networks:
“Cynicism formulates issues clearly, but only to dismiss them.”
—Mason Cooley (b. 1927)
“Culture’s essential service to a religion is to destroy intellectual idolatry, the recurrent tendency in religion to replace the object of its worship with its present understanding and forms of approach to that object.”
—Northrop Frye (b. 1912)
“To be perfectly, brutally honest, those of us who are still carrying diaper everywhere we go are not at our most scintillating time of life....We need to remember that at one time in our lives, we all had senses of humor and knew things that were going on in the world. And if we just keep our social networks open, there will be people ready to listen when we once again have intelligent things to say.”
—Louise Lague (20th century)