diff options
author | Eduardo Julian | 2019-11-21 23:05:27 -0400 |
---|---|---|
committer | Eduardo Julian | 2019-11-21 23:05:27 -0400 |
commit | b7cff25b71f024a4da86603e5a0b432fae1601e6 (patch) | |
tree | df4929342cd2cba1d89122115cd0dbb85841bb8d /documentation/research/machine_learning.md | |
parent | fa40cabbf361b717023183b57eed3bb72919a080 (diff) |
Ported JVM host extension generation to the new JVM bytecode machinery.
Diffstat (limited to '')
-rw-r--r-- | documentation/research/machine_learning.md | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/documentation/research/machine_learning.md b/documentation/research/machine_learning.md index cc2d4d548..fe5871b87 100644 --- a/documentation/research/machine_learning.md +++ b/documentation/research/machine_learning.md @@ -10,6 +10,7 @@ # Reference +1. ["Multi-Level Intermediate Representation" Compiler Infrastructure](https://github.com/tensorflow/mlir) 1. [Sampling can be faster than optimization](https://www.pnas.org/content/116/42/20881) 1. [Layer rotation: a surprisingly powerful indicator of generalization in deep networks](https://arxiv.org/abs/1806.01603v2) 1. https://nostalgebraist.tumblr.com/post/185326092369/the-transformer-explained @@ -72,6 +73,8 @@ # Differentiable programming +1. [The principles behind Differentiable Programming - Erik Meijer](https://www.youtube.com/watch?v=lk0PhtSHE38) +1. [Kotlin∇: Type-safe Symbolic Differentiation for Kotlin](https://github.com/breandan/kotlingrad) 1. [Differentiable Programming Manifesto](https://github.com/apple/swift/blob/master/docs/DifferentiableProgramming.md) 1. [Backpropagation in the Simply Typed Lambda-calculus with Linear Negation](https://arxiv.org/abs/1909.13768) 1. [One-and-a-Half Simple Differential Programming Languages](https://pages.cpsc.ucalgary.ca/~robin/FMCS/FMCS2019/slides/GordonPlotkin-FMCS2019.pdf) |