Grammar fixes in Deep Learning with Torch.ipynb

it's -> its

Deep Learning with Torch.ipynb

@@ -479,13 +479,13 @@
     "##### Review of what you learnt so far\n",
     "* Network can have many layers of computation\n",
     "* Network takes an input and produces an output in the :forward pass\n",
-    "* Criterion computes the loss of the network, and it's gradients w.r.t. the output of the network.\n",
-    "* Network takes an (input, gradients) pair in it's backward pass and calculates the gradients w.r.t. each layer (and neuron) in the network.\n",
+    "* Criterion computes the loss of the network, and its gradients w.r.t. the output of the network.\n",
+    "* Network takes an (input, gradients) pair in its backward pass and calculates the gradients w.r.t. each layer (and neuron) in the network.\n",
     "\n",
     "##### Missing details\n",
     "> A neural network layer can have learnable parameters or not.\n",
     "\n",
-    "A convolution layer learns it's convolution kernels to adapt to the input data and the problem being solved.  \n",
+    "A convolution layer learns its convolution kernels to adapt to the input data and the problem being solved.  \n",
     "A max-pooling layer has no learnable parameters. It only finds the max of local windows.\n",
     "\n",
     "A layer in torch which has learnable weights, will typically have fields .weight (and optionally, .bias)"
@@ -633,7 +633,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Now, to prepare the dataset to be used with __nn.StochasticGradient__, a couple of things have to be done according to it's [documentation](https://github.com/torch/nn/blob/master/doc/training.md#traindataset).\n",
+    "Now, to prepare the dataset to be used with __nn.StochasticGradient__, a couple of things have to be done according to its [documentation](https://github.com/torch/nn/blob/master/doc/training.md#traindataset).\n",
     "1. The dataset has to have a :size() function.\n",
     "2. The dataset has to have a [i] index operator, so that dataset[i] returns the ith sample in the datset.\n",
     "\n",
@@ -1025,7 +1025,7 @@
    "source": [
     "You can see the network predictions. The network assigned a probability to each classes, given the image.\n",
     "\n",
-    "To make it clearer, let us tag each probability with it's class-name:"
+    "To make it clearer, let us tag each probability with its class-name:"
    ]
   },
   {