Although the paper deals with visual applications, in principle it should be possible to extend to text and other data sources (input data is projected into numeric form ). "A similar setup to the CartPole experiment…
30% of Google ML workload is LSTM. Only 5% is CNN. https://cloud.google.com/blog/products/gcp/an-in-depth-look-... Schmidhuber should have gotten the award too.
Although the paper deals with visual applications, in principle it should be possible to extend to text and other data sources (input data is projected into numeric form ). "A similar setup to the CartPole experiment…
30% of Google ML workload is LSTM. Only 5% is CNN. https://cloud.google.com/blog/products/gcp/an-in-depth-look-... Schmidhuber should have gotten the award too.