Revisiting our computational exercises with a machine learning approach

In this section, let's apply all the knowledge we've acquired so far. Try using a real-world dataset, as discussed in Chapter 6, Working with CUDA and PyCUDA, and use the Solution Assistance section to get started with the following exercises to step up your machine learning game:

1. Use TensorFlow or PyTorch to implement Karl Pearson's correlation coefficient. Based on the computed coefficient, use machine learning to predict the probability of a certain population in a region to be affected with a correlated disease. You can also use image datasets of tobacco and its linked diseases to widen the scope of the study.
2. Create a machine learning model with TensorFlow or PyTorch for the prediction of diabetes. Use real-world data after testing your model.
3. Create a machine learning model with TensorFlow...