-
Hey,
I think it would be cool if we could specify when the recurrent network should stop updating its hidden state. For example if my sequences have max length 100, and a particular example has lengt…
-
Hi guys, I'm trying to model count data both spatially and temporally but I'm running into some trouble when the number of variables increases. My data is across ~200 regions and 10 time points but wh…
-
I'm trying to implement a Convolutional - LSTM.
It's a recurrent layer which accepts an image as input and uses a convolution to calculate the various gates in the LSTM.
So I'm trying to subclass `…
-
The ptrace method does not return the correct normalization for non-density matrix operators (e.g. Hamiltonians. In fact, the resulting operator is incorrectly multiplied by a value of Q.shape[0]:
`…
-
Besides the #3 , I have a question on matrix multiply. What is its performance compared to the hardcoded library functions? If it is something like a third, then it might be possible to speed it up by…
-
layers.py, on which most of the nntools code is based, has always been geared towards feed-forward neural networks. We should look into recurrent neural networks as well. Personally I don't have a lot…
-
-
[creating a separate issue for this. I expect this issue will be up for a while].
The new CUDA "v2" API has been supported since v4.0 of the CUDA toolkit (i.e. for quite a while; we are now on 7), a…
-
We have discussed the need for more types above `Array`, e.g. in #750. Candidates include `DenseArray`, `UniformDenseArray`, `ContiguousArray`, `UniformAccessArray`, etc.
-
I prepared the interpolation interface to make this implementation simple.
I thought that I just needed to invert our interpolating matrix kxN \phi, but of course it turns out that N>>k, and therefor…