From 1b9d24ed6085bac806bb0a38e7c32204f516ec66 Mon Sep 17 00:00:00 2001 From: Asif Hazrat Date: Thu, 25 Jul 2019 15:43:35 -0500 Subject: [PATCH] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 12a55e8..9415b0d 100644 --- a/README.md +++ b/README.md @@ -4,7 +4,7 @@ EvoGrad is a lightweight tool for differentiating through expectation, built on top of PyTorch. Tools that enable fast and flexible experimentation democratize and accelerate machine learning research. -However, one field that so far has not been greatly impacted by automatic differentiation tools is evolutionary computation +However, one field that so far has not been greatly impacted by automatic differentiation tools is evolutionary computation. The reason is that most evolutionary algorithms are gradient-free: they do not follow any explicit mathematical gradient (i.e., the mathematically optimal local direction of improvement), and instead proceed through a generate-and-test heuristic. In other words, they create new variants, test them out, and keep the best.