diff --git a/notebooks/2_convolutions/01_losses.ipynb b/notebooks/2_convolutions/01_losses.ipynb
index 282b60af..04e4e28a 100644
--- a/notebooks/2_convolutions/01_losses.ipynb
+++ b/notebooks/2_convolutions/01_losses.ipynb
@@ -457,7 +457,7 @@
     "\n",
     "- For regression models, typically use a MSE\n",
     "- For classification, use CrossEntropyLoss (note: this might be implemented different in other libraries like Tensorflow!)\n",
-    "- For multiclass, use BinaryCrossEntropy\n",
+    "- For multilabel, use BinaryCrossEntropy\n",
     "\n",
     "There are other, more complex losses for more complex usecases but these three will cover 80% of your needs."
    ]