From 30b1ca35ede18b31fa7b121ed03f6e75304502db Mon Sep 17 00:00:00 2001
From: Jianjia Ma <majianjia@live.com>
Date: Wed, 23 Jun 2021 11:47:24 +0100
Subject: [PATCH] Add tips

---
 README.md | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/README.md b/README.md
index 572b46ca..c6d07bee 100644
--- a/README.md
+++ b/README.md
@@ -183,6 +183,11 @@ x = Dense(32)(x)
 x = Relu()(x)
 ~~~
 
+## Tips - improving accuracy
+- Attaching an BatchNormalization after each convolutional layer limit the activation range thus help quantisation. BN add no extra computation in NNoM. 
+- Dont train too much epoch. Large epoch number increases extreme number in activation -> lower the quantisation resolution.
+- Leave enough data for bottleneck - do not compress data at before the output of a model, infomation will be lost when it is quantised. 
+
 ## Contacts
 Jianjia Ma
 majianjia@live.com