I have selected a 2-class classification problem with our classic "Wine Quality" Dataset. So we have Wine Quality dataset. How to Balance the data, so that they have equal numbers of data points from each class, e.g., by duplicating randomly chosen members of the minority class and adding a little random noise. Use 70% of the data for training, and 30% for testing, ensuring that both sets are balanced. How to Train a shallow feedforward neural network (with sigmoidal node functions and one hidden layer with twice as many nodes as the input dimensionality) using back-propagation with ADAM optimizer, while keeping track of performance on test data during the training process. How to Repeat the experiment ten times, each time starting with a different set of randomly initialized weights; store these initial weights. Summarize the results using one graph, plotting the average accuracy (on the y-axis) against log(number of weight updates), for training data and for test data; the graph will hence show two curves. Also how to show the confusion matrix.

How to write the code for the same in PYTHON language? How to solve the above problem. Please explain in detail.

Below is the link of dataset,

https://online.stat.psu.edu/onlinecourses/sites/stat508/files/Wine_data.xlsx