im working on a project in which I have to make a multi-layer perceptron with two hidden layers with 3 nodes in each. The target value in my data contains 8 unique values/classes. One of the tasks states "For the most popular class CYT plot weight values per iteration for the last layer (3 weights and bias)". My question is "does this statement make sense"? I can access the weights and biases of a layer but I don't get what are weight values for a specific class and how to access them
A common model used for this kind of classification task is to have one output neuron per class. So, for example, neuron 1 may have a loss function that is related to outputting "1" for examples of class 1, and "0" for examples of other classes. Neuron 2 may be asked to do the same, but for class 2 rather than class 1.
If you use a model of this kind, you can pull the weights for each neuron in the final output layer. It sounds like this is what you are being asked to plot.