Problem
We have the "Wine quality" dataset. Balance the data, so that you 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. 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 and Evolution Strategies algorithm depending on case (4+20) ES, while keeping track of performance on test data during the training process. Repeat the experiment ten times, each time starting with a different set of randomly initialized weights; store these initial weights for future.
Provide results averaged over ten trials. Show the confusion matrices for both back-propagation with ADAM optimizer and Evolution Strategies algorithm depending on case (4+20) ES(for training data and test data). Compare both the result and show one graph with training and testing results for both algorithms.
How to write code for both algorithms in PYTHON language?