From 0d1ab038615460f175a63588607be8aeff2a932e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mathieu=20Dagr=C3=A9ou?=
 <77896657+MatDag@users.noreply.github.com>
Date: Fri, 18 Oct 2024 11:43:30 +0200
Subject: [PATCH] FIX ref

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

diff --git a/README.md b/README.md
index 9c8484e..cab6e44 100644
--- a/README.md
+++ b/README.md
@@ -74,7 +74,7 @@ each line in $z$ is independently regularized with the strength $\exp(x_j)$.
 
 ### 3 - Data cleaning
 
-This problem was first introduced by [Franceschi et al., 2017](https://arxiv.org/abs/1703.01785).
+This problem was first introduced by [Franceschi et al. (2017)](https://arxiv.org/abs/1703.01785).
 In this problem, the data is the MNIST dataset.
 The training set has been corrupted: with a probability $p$, the label of the image $`y\in\{1,\dots,10\}`$ is replaced by another random label between 1 and 10.
 We do not know beforehand which data has been corrupted.