Start with an analogy. Then delve into CUDA with some pytorch code to demonstrate why we use GPUs instead of just CPUs.

REFERENCES
[1] Why GPU’s work well in deep learning: https://www.quora.com/WhyareGPUswe...
[2] Matrix math on a GPU: http://www.ijcee.org/vol9/949E1621.pdf
[3] GPUs are not necessarily faster than CPUs: https://www.quora.com/WhyareGPUsmo...
[4] Code for difference:   / usingpytorchandcudaforlargecomputati...  
[5] GPU memory architecture:   / cudagpumemoryarchitecture