From 04a564d7d0841cd4db7926a64be0cf8816945cdd Mon Sep 17 00:00:00 2001
From: PENG Bo <33809201+BlinkDL@users.noreply.github.com>
Date: Wed, 22 Mar 2023 23:18:15 +0800
Subject: [PATCH] Update README.md

---
 README.md | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 2fe5597..cc167a1 100644
--- a/README.md
+++ b/README.md
@@ -212,7 +212,9 @@ out.write(ss + "\n")
 
 4. Aside from 2d rotation, we can try other Lie groups such as 3d rotation ( SO(3) ). Non-abelian RWKV lol.
 
-5. RWKV might be great on analog devices (search for Analog Matrix-vector multiplication & Photonic Matrix-vector multiplication). RNN is very hardware-friendly (in-memory processing?). Can be a SNN too (https://github.com/ridgerchu/SpikeGPT). I wonder if it can be optimized for quantum computation.
+5. RWKV might be great on analog devices (search for Analog Matrix-vector multiplication & Photonic Matrix-vector multiplication). The RNN mode is very hardware-friendly (processing-in-memory). Can be a SNN too (https://github.com/ridgerchu/SpikeGPT). I wonder if it can be optimized for quantum computation.
+
+6. Trainable initial hidden state (xx aa bb pp xx).
 
 ### Vision Tasks