From aef3d37e29d601b4959b4824a96a37cc4ba7a6eb Mon Sep 17 00:00:00 2001 From: fuzzythecat Date: Tue, 20 Mar 2018 12:07:04 +0900 Subject: [PATCH] Fix typo --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index e9a9dea..6dbd904 100644 --- a/README.md +++ b/README.md @@ -28,7 +28,7 @@ relevant to this dataset as well. Hence, the best idea might be to train a linea overfit if we were to try to fine-tune through the full network.  New dataset is small but very different from the original dataset. Since the data is small, it is likely best to only train a -linear classifier. Since the dataset is very different, it might not be best to train the classifier form the top of the network, +linear classifier. Since the dataset is very different, it might not be best to train the classifier from the top of the network, which contains more dataset-specific features. Instead, it might work better to train the SVM classifier from activations somewhere earlier in the network.