The Essential Tools of Scientific Machine Learning
stochasticlifestyle.com
The Essential Tools of Scientific Machine Learning
1–10 of 21 posts
Re: The Essential Tools of Scientific Machine Learning
#2Very much Julia oriented. Nice that Julia is catching up with other. This one however is missing comparison with R tools. I guess R would also be quite green on the "Quick Summary Table".
Re: The Essential Tools of Scientific Machine Learning
#3Very much Julia oriented. Nice that Julia is catching up with other. This one however is missing comparison with R tools. I guess R would also be quite green on the "Quick Summary Table".
Do you have an example of an R automatic differentiation package which has an ecosystem of compatible tools like PDE solvers, automatic sparsity detection, convolutional neural networks, and global sensitivity analysis? If you have one I'll add it to the list. But the ones that I know are things like madness [1], radx [2], and TMB [3], all of which are good AD systems in their own right (the latter most having some good parallelism), but are missing most of the relevant features for a discussion of scientific ML (but would be great for standard ML). I could also point to autodiffr [4], but that's using Julia to autodiff R.
But if there's one I missed I'd love to hear about it and start tracking the project!
[1] https://cran.r-project.org/web/packages/madness/vignettes/in...
[2] https://rdrr.io/github/quantumelixir/radx/man/radx-package.h...
[3] https://www.jstatsoft.org/article/view/v070i05/v70i05.pdf
[4] https://non-contradiction.github.io/autodiffr/index.html
Re: The Essential Tools of Scientific Machine Learning
#4Very much Julia oriented. Nice that Julia is catching up with other. This one however is missing comparison with R tools. I guess R would also be quite green on the "Quick Summary Table".
Do you have an example of an R automatic differentiation package which has an ecosystem of compatible tools like PDE solvers, automatic sparsity detection, convolutional neural networks, and global sensitivity analysis? If you have one I'll add it to the list. But the ones that I know are things like madness [1], radx [2], and TMB [3], all of which are good AD systems in their own right (the latter most having some g…
I don't, but maybe a disclaimer on R in this article could bring those who could share their experience with R?
Re: The Essential Tools of Scientific Machine Learning
#5How do I, with a very nice AMD GPU, and running on Windows, play around with any sort of GPU accelerated learning for anything? Last I knew, pretty much nothing worked with either of those caveats.
Re: The Essential Tools of Scientific Machine Learning
#6Very much Julia oriented. Nice that Julia is catching up with other. This one however is missing comparison with R tools. I guess R would also be quite green on the "Quick Summary Table".
Do you have an example of an R automatic differentiation package which has an ecosystem of compatible tools like PDE solvers, automatic sparsity detection, convolutional neural networks, and global sensitivity analysis? If you have one I'll add it to the list. But the ones that I know are things like madness [1], radx [2], and TMB [3], all of which are good AD systems in their own right (the latter most having some g…
I would be curious to know whether I have been the only one using TMB in production in a tech company. A tricky piece of software, but very powerful.
Re: The Essential Tools of Scientific Machine Learning
#7Good thing I did not ever "Give Up On Julia"™! So happy to see numerical programming breaking new grounds like this
Re: The Essential Tools of Scientific Machine Learning
#8How do I, with a very nice AMD GPU, and running on Windows, play around with any sort of GPU accelerated learning for anything? Last I knew, pretty much nothing worked with either of those caveats.
Running Windows is perfectly fine; the major libraries for GPU-accelerated autodiff and networks (CUDNN with Pytorch or Tensorflow) have great support nowadays. It's the AMD GPU that remains essentially useless, as of 2019. If you want to get into the game, I'd recommend buying a middle-of-the-road NVIDIA GPU like the RTX2060.
For toying with autodiff and basic CNNs, CPU works just fine by the way...
Re: The Essential Tools of Scientific Machine Learning
#9How do I, with a very nice AMD GPU, and running on Windows, play around with any sort of GPU accelerated learning for anything? Last I knew, pretty much nothing worked with either of those caveats.
Running Windows is perfectly fine; the major libraries for GPU-accelerated autodiff and networks (CUDNN with Pytorch or Tensorflow) have great support nowadays. It's the AMD GPU that remains essentially useless, as of 2019. If you want to get into the game, I'd recommend buying a middle-of-the-road NVIDIA GPU like the RTX2060. For toying with autodiff and basic CNNs, CPU works just fine by the way...
>It's the AMD GPU that remains essentially useless, as of 2019
I guess more important question... Whyyyyyyyyyyyyy
Re: The Essential Tools of Scientific Machine Learning
#10How do I, with a very nice AMD GPU, and running on Windows, play around with any sort of GPU accelerated learning for anything? Last I knew, pretty much nothing worked with either of those caveats.
Running Windows is perfectly fine; the major libraries for GPU-accelerated autodiff and networks (CUDNN with Pytorch or Tensorflow) have great support nowadays. It's the AMD GPU that remains essentially useless, as of 2019. If you want to get into the game, I'd recommend buying a middle-of-the-road NVIDIA GPU like the RTX2060. For toying with autodiff and basic CNNs, CPU works just fine by the way...
>It's the AMD GPU that remains essentially useless, as of 2019.
This appears to finally be starting to change. See:
https://github.com/RadeonOpenCompute/ROCm
https://github.com/ROCmSoftwarePlatform/tensorflow-upstream/