aboutsummaryrefslogtreecommitdiff
path: root/documentation/research/machine_learning.md
diff options
context:
space:
mode:
authorEduardo Julian2019-10-27 01:10:13 -0400
committerEduardo Julian2019-10-27 01:10:13 -0400
commitaab604028e117e505bc408f69dc416fe6d9f46a7 (patch)
tree5184e162e8524ea687d5567656029197742b9302 /documentation/research/machine_learning.md
parent87a9d756a9e94fb81fc14fea39df3e20d394afdb (diff)
Almost completely ported JVM runtime generation to the new JVM bytecode machinery.
Diffstat (limited to 'documentation/research/machine_learning.md')
-rw-r--r--documentation/research/machine_learning.md2
1 files changed, 2 insertions, 0 deletions
diff --git a/documentation/research/machine_learning.md b/documentation/research/machine_learning.md
index 1c299032a..9b38b3398 100644
--- a/documentation/research/machine_learning.md
+++ b/documentation/research/machine_learning.md
@@ -10,6 +10,7 @@
# Reference
+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
1. [HyperE: Hyperbolic Embeddings for Entities](https://hazyresearch.github.io/hyperE/)
@@ -71,6 +72,7 @@
# Differentiable programming
+1. [One-and-a-Half Simple Differential Programming Languages](https://pages.cpsc.ucalgary.ca/~robin/FMCS/FMCS2019/slides/GordonPlotkin-FMCS2019.pdf)
1. [Differentiable Programming Mega-Proposal](https://forums.swift.org/t/differentiable-programming-mega-proposal/28547)
1. https://fluxml.ai/2019/02/07/what-is-differentiable-programming.html
1. https://github.com/breandan/kotlingrad