DTSC71/31-301 Applied Machine Learning Assignment 2 Weighting: 20% Due Date: 5 pm, Friday the 16th of July (end of Week 9), 2021. Overview Your task is to objectively examine the efficacy of Deep Neural Networks across two different problem domains. Models have been proposed for each problem. You are required to objectively improve these models. Both are classification problems. One model predicts which category newsgroup text belongs to. Similarly in the other problem a model has been proposed to predict which of 10 categories an image belongs to. Both models were made available as Notebooks and can be downloaded from iLearn. In examining the efficacy of each model, you are expected to create a benchmark and then build the best possible model that you can in Spyder for each problem (starting from the model supplied). Remember a good model sits right at the border between underfitting and overfitting – it maximizes accuracy while minimizing the network si
ze. Your report should include a comparison of the effort you put into the development of your final models. Your report should contain recommendations for future modellers on how to improve third party models in an objective manner. Report Template Aim to produce a structured report that suitably reflects your recommendations given the task of improving an already existing model for a problem. Ensure your written comparisons are objectively stated. Focus on explaining why you made the decisions and choices you made. I can see what you did in the code you upload… what I want to know is why you made those choices. Marking thoughts I value conciseness and elegance in coding. I value your explanations as to why you made the choices you made. I value the quality of the model – higher test accuracy and a lower number of network parameters makes a better model. To achieve this takes considerable effort and thought, which will be rewarded. Surprise me.