fix link from gan to diffusion

examples/deep_convolutional_gan.ipynb

@@ -10,7 +10,7 @@
     "\n",
     "This example builds a Generative Adversarial Network (GAN) using convolutional layers in the discriminator and generator.\n",
     "\n",
-    "In practice GANs are now used fairly rarely, because they're quite tricky to train stably. Modern applications tend to use [score-based diffusions](../score_based_diffusion/) instead. Nonetheless, here's an example for how we might set up a GAN in Equinox.\n",
+    "In practice GANs are now used fairly rarely, because they're quite tricky to train stably. Modern applications tend to use [score-based diffusions](score_based_diffusion.ipynb) instead. Nonetheless, here's an example for how we might set up a GAN in Equinox.\n",
     "\n",
     "This example is an implementation based on the paper: Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks.\n",
     "\n",