Jonathan Zhouhan LIN
Jonathan Zhouhan LIN
The Frobenius norm has a `sqrt()` operation, which is not necessary if we are optimizing it. The difference is just a matter of speed I think.
Sorry for the late reply. You are right, the above code in the first post should raise a dimension mismatch error. Yes. I think the `sqrt` could be removed to...
The "batched_dot" is just the [batched_dot()](http://deeplearning.net/software/theano/library/tensor/basic.html#theano.tensor.batched_dot) function in Theano. $M_h$ and $M_p$ are of shape (u, r); $F_h$ and $F_p$ are of shape (h, r); where h is the number...
The 8.0 and 5.1 are different versions, but we were not able to find the original 5.1 version from the web. According to [Liu and Zhang. 2017b], who is using...
Yes. Each newer version is a superset of older versions, sometimes with minor corrections to errors in previous versions. See https://catalog.ldc.upenn.edu/LDC2013T21 On Thu, Mar 26, 2020 at 5:03 PM Kaiyu...
Will this PR be merged in the future?
Thanks for letting me know! Zhouhan On Thu, Apr 12, 2018 at 2:12 PM, Mathieu Germain wrote: > The whole smartdispatch seems to be somewhat on hold so I can't...
Thanks for the clarification. So is there a tutorial on how to use slurm in clusters like cedar?