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:
“I can never bring you to realize the importance of sleeves, the suggestiveness of thumb-nails, or the great issues that may hang from a boot-lace.”
—Sir Arthur Conan Doyle (1859–1930)
“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)
“The community and family networks which helped sustain earlier generations have become scarcer for growing numbers of young parents. Those who lack links to these traditional sources of support are hard-pressed to find other resources, given the emphasis in our society on providing treatment services, rather than preventive services and support for health maintenance and well-being.”
—Bernice Weissbourd (20th century)