add torchviz library to draw computational graph

[zzowenzz]

Description of changes:

By submitting this pull request, I confirm that you can use, modify,
copy, and redistribute this contribution, under the terms of your
choice.

Add several paragraph to discuss the computational graph in pytorch and show an example of using torchviz to automatically generate a computational graph. Here is an example and a screenshot of the generated graph:

from torchviz import make_dot

# Create some tensors and perform operations
x = torch.tensor([2.0], requires_grad=True)
y = torch.tensor([3.0], requires_grad=True)
z = x + y
output = z * z

# Visualise the computational graph
dot = make_dot(output, params={"x": x, "y": y})

# Save the graph as a PDF file
dot.render("computational_graph", format="png")

generated graph