School of Computing and Information Systems The University of Melbourne
COMP90049 Introduction to Machine Learning (Semester 1, 2022) Week 2: Workshop
Considering the following problems:
(i) Skin cancer screening test
Copyright By PowCoder代写 加微信 powcoder
(ii) Building a system that guesses what the weather (temperature, precipitation, etc.) will be like tomorrow
(iii) Predicting products that a customer would be interested in buying, based on other purchases that customer has previously made
1. Identify the ¡°concept¡± we might attempt to ¡°learn¡± for each problem (Task Identification)
2. For each problem-task, identify what the ¡°instances¡± and ¡°attributes¡± might consist of (Choosing the Data Representative)
3. For each problem-task, conjecture whether a typical strategy is likely to use ¡°supervised¡± or ¡°unsupervised¡± Machine Learning (Picking a Suitable Model)
4. [OPTIONAL] For each problem-task, consider how easy or difficult it would be to make a model that generalizes to new cases. For example, could you predict the weather in any city in the world, or just in one specific city?
5. [OPTIONAL] What kinds of assumptions might a machine learning model make when tackling these problems?
6. What is discretisation, and where might it be used? Discretise attribute C of the following dataset according to the given methods (breaking ties where necessary).
(i) Equal width
(ii) Equal frequency
(iii) k-means
程序代写 CS代考 加微信: powcoder QQ: 1823890830 Email: powcoder@163.com