Paul Shen

icon indicating a website link luminescentai.com icon indicating an email [email protected]

icon company Luminescent AI icon location Cofounder at Luminescent AI | Stanford EE alum

Results 16 comments of Paul Shen

Is there a pretrained model supporting extraction of symptoms and diseases?

Thank you I appreciate it.

Requesting rotated MNIST dataset

@Dsantra92 You can try our [EquivariantOperators.jl](https://aced-differentiate.github.io/EquivariantOperators.jl/) [Tutorials on colab](https://colab.research.google.com/drive/17JZEdK6aALxvn0JPBJEHGeK2nO1hPnhQ#scrollTo=4utBHhoeHzRY) [Paper Preprint](http://arxiv.org/abs/2108.09541)

Requesting rotated MNIST dataset

Thanks will do

Requesting rotated MNIST dataset

Thanks @Dsantra92 I believe @CarloLucibello dug up the subfolder containing output from the script in the same format as MNIST data

Error with new testing with raw text feature

Thank you both. I appreciate it.

Solution handling for `ComponentArrays`: how to extract a variable by name?

Doesn't `sol(t).x` work already?

L-BFGS algorithm request

Thanks I found updated implementation in Optim.jl https://github.com/JuliaNLSolvers/Optim.jl/blob/master/src/multivariate/solvers/first_order/l_bfgs.jl Doesn't look too hard to port to Optimisers.jl? We can omit linesearch. Flux assumes each function evaluation is expensive.

CUDA app by PackageCompiler hangs at runtime on Ubuntu / Debian

Update: problem arises on Google Colab and not in AWS VMs. Problem persists with julia11.4 cuda.jl5.7 . But I need this to work on Colab! Happy to pay couple hours...

`numbertype` option not forwarded to STL format

Thanks I did PR for obj - numbertype wasn't passed to objread

`numbertype` option not forwarded to STL format

Ok done!