Fix typos regarding SGD, and make links specific

Author: jayanthkoushik

Deep Learning with PyTorch.ipynb

@@ -720,14 +720,14 @@
     "- updating the weights of the network\n",
     "\n",
     "The simplest update rule used in practice is the Stochastic Gradient Descent (SGD):\n",
-    "> `weight = weight = learning_rate * gradient`\n",
+    "> `weight = weight - learning_rate * gradient`\n",
     "\n",
     "We can implement this using simple python code:\n",
     "\n",
     "```python\n",
     "learning_rate = 0.01\n",
     "for f in net.parameters():\n",
-    "    f.data.add_(f.grad * learning_rate)\n",
+    "    f.data.sub_(f.grad * learning_rate)\n",
     "```\n",
     "\n",
     "However, as you use neural networks, you want to use various different update rules such as SGD, Nesterov-SGD, Adam, RMSProp, etc.\n",
@@ -1199,9 +1199,9 @@
    "source": [
     "## Where do I go next?\n",
     "\n",
-    "- [Train neural nets to play video games](https://github.com/pytorch/tutorials)\n",
-    "- [Train a state-of-the-art ResNet network on imagenet](https://github.com/pytorch/examples)\n",
-    "- [Train an face generator using Generative Adversarial Networks](https://github.com/pytorch/examples)\n",
+    "- [Train neural nets to play video games](https://github.com/pytorch/tutorials/blob/master/Reinforcement%20(Q-)Learning%20with%20PyTorch.ipynb)\n",
+    "- [Train a state-of-the-art ResNet network on imagenet](https://github.com/pytorch/examples/tree/master/imagenet)\n",
+    "- [Train an face generator using Generative Adversarial Networks](https://github.com/pytorch/examples/tree/master/dcgan)\n",
     "- [Train a word-level language model using Recurrent LSTM networks](https://github.com/pytorch/examples/tree/master/word_language_model)\n",
     "- [More examples](https://github.com/pytorch/examples)\n",
     "- [More tutorials](https://github.com/pytorch/tutorials)\n",