From d1ad8db625d0a870ef7bd6bcbcbcb7342953e54c Mon Sep 17 00:00:00 2001
From: Yao Lu <luyaocns@gmail.com>
Date: Sat, 9 May 2020 16:40:26 +0800
Subject: [PATCH] add to docs

---
 docs/src/training/optimisers.md | 13 +++++++++++++
 1 file changed, 13 insertions(+)

diff --git a/docs/src/training/optimisers.md b/docs/src/training/optimisers.md
index 5ed083ee..25cfd3ce 100644
--- a/docs/src/training/optimisers.md
+++ b/docs/src/training/optimisers.md
@@ -140,3 +140,16 @@ ExpDecay
 InvDecay
 WeightDecay
 ```
+
+## Gradient Clipping
+
+Gradient clipping is useful for training recurrent neural networks, which have a tendency to suffer from the exploding gradient problem. An example usage is
+
+```julia
+opt = Optimiser(ClipValue(1e-3), ADAM(1e-3))
+```
+
+```@docs
+ClipValue
+ClipNorm
+```
\ No newline at end of file