From 255643868e5a2c4b63f14c27221ce01a77c9e316 Mon Sep 17 00:00:00 2001
From: Ziming Liu <zmliu@mit.edu>
Date: Sat, 4 May 2024 17:52:01 -0400
Subject: [PATCH] Update README.md

---
 README.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/README.md b/README.md
index fb2ab9ff..4e9fbd95 100644
--- a/README.md
+++ b/README.md
@@ -11,6 +11,8 @@ Kolmogorov-Arnold Networks (KANs) are promising alternatives of Multi-Layer Perc
 ## Accuracy
 **KANs have faster scaling than MLPs. KANs have better accuracy than MLPs with fewer parameters.**
 
+Please set torch.set_default_dtype(torch.float64) if you want high precision.
+
 **Example 1: fitting symbolic formulas**
 <img width="1824" alt="Screenshot 2024-04-30 at 10 55 30" src="https://github.com/KindXiaoming/pykan/assets/23551623/e1fc3dcc-c1f6-49d5-b58e-79ff7b98a49b">