Add explanation for using boolean to count correct predictions

Author: MisaOgura

intro-neural-networks/gradient-descent/GradientDescent.ipynb

@@ -154,7 +154,11 @@
     "            else:\n",
     "                print(\"Train loss: \", loss)\n",
     "            last_loss = loss\n",
+    "            \n",
+    "            # Converting the output (float) to boolean as it is a binary classification\n",
+    "            # e.g. 0.95 --> True (= 1), 0.31 --> False (= 0)\n",
     "            predictions = out > 0.5\n",
+    "            \n",
     "            accuracy = np.mean(predictions == targets)\n",
     "            print(\"Accuracy: \", accuracy)\n",
     "        if graph_lines and e % (epochs / 100) == 0:\n",