From f6cb205a7b8d2bc001252bf2452c154edd644481 Mon Sep 17 00:00:00 2001
From: jloveric <john.loverich@gmail.com>
Date: Wed, 19 Jun 2024 09:09:22 -0700
Subject: [PATCH] Update readme

---
 README.md | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/README.md b/README.md
index b733118..e789913 100644
--- a/README.md
+++ b/README.md
@@ -292,6 +292,12 @@ The polynomial last layer is the same as that used in the convolution.
 |9 | 0.990 | 0.989
 |10| 0.990 | 0.990
 
+## MNIST Block 3D polynomial
+Basics implemented, needs to be made more efficient and model needs to change a bit. Currently uses a single NxNxN polynomial
+with 3 inputs (grayscale color, x, y) and 10 outputs to solve mnist. Not performant, but will work on it.
+```
+python3 examples/block_mnist.py accelerator='cuda' batch_size=64 optimizer.lr=1e-3
+```
 
 ## CIFAR100 (convolutional)