Postgraduate Course: Introductory Applied Machine Learning (INFR11152)
|School||School of Informatics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 11 (Postgraduate)
|Course type||Online Distance Learning
||Availability||Not available to visiting students
|Summary||*This course is for distance learning students within the School of Informatics and students on the Data Science, Technology & Innovation programme*.
Organisations seek to make better decisions by examining their data with an aim to discovering and/or drawing conclusions about the information contained within. This course is about the principled application of machine learning techniques to extracting information from data. The main area that will be discussed is supervised learning, which is concerned with learning to predict an output, given inputs. A second area of study is unsupervised learning, where we wish to discover the structure in a set of patterns, i.e. there is no output "teacher signal". The primary aim is to provide the student with a set of practical tools that can be applied to solve real - world problems in machine learning, coupled with an appropriate, principled approach to formulating a solution.
This distance-based course is aligned with the on-campus Introductory Applied Machine Learning course (INFR10069), which uses a flipped classroom delivery approach. Distance students will cover the same materials, have the same coursework, engage in the same classroom activities (but using Collaborate) and take the same exam as the on-campus students.
This course is delivered using "flipped-classroom" methods, and will be looking for student feedback during the course how this is working for you. Intellectual content will be delivered via a combination of online short video segments (overall, per topic, approximately the same length as a traditional lecture). Some of the topics have online quizzes associated with them, intended for you to review your understanding. During some of the lecture slots, we will have other activities to review the topic material.
1) Introductory Lecture
2) Maths and Probability
3) Thinking About Data
4) Naive Bayes
5) Decision Trees
6) Generalisation and Evaluation
7) Linear Regression
8) Logistic regression
9) Optimisation and Regularisation
10) Support Vector Machines
11) Nearest Neighbours
13) Gaussian Mixture Models
14) Principal Components Analysis
15) Hierarchical Clustering
16) Neural Networks
We will also use a modern machine learning programming environment.
Entry Requirements (not applicable to Visiting Students)
||Other requirements|| None
Course Delivery Information
|Academic year 2017/18, Not available to visiting students (SS1)
|Course Start Date
|Learning and Teaching activities (Further Info)
Lecture Hours 20,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
||Written Exam: 75%
Formative coursework: each online lecture will have an associated online self-assessment quiz. There will also be Tutorial exercises and Pair-programming lab exercises.
There will be 4 coursework assignments in total. Each are designed to take the student 5 hours work. The mark breakdown is 2.5%, 7.5%, 7.5%, 7.5%.
The coursework assignments are a key part of the student engagement strategy for online learning, involving peer-comment and discussion which is a assessed for a small fraction of the mark (15% of each coursework mark, so 4.5% of the overall course mark).
Written Exam 75 %, Coursework 25 %, Practical Exam 0 %
||We plan a rich and well-resourced level of engagement between distance education students and world-leading Informatics teaching and research staff:
- Extensive use of the School and University level virtual learning environments (VLE) such as Learn and social platform is planned.
- Course forums will allow students to ask questions to both teaching staff and to other students.
- Online peer-feedback as well as tutor-feedback is designed into all the tutorials, labs and coursework (formative and summative).
The NB platform (nb.mit.edu) is the place to ask questions about the course materials: topics slides and videos, the labs, tutorials and the assignments. Sign up for it at the link in the announcement. We encourage students to answer questions if you can - it is a great learning experience to explain something to another student. The forum is monitored and responded to by the lecturer and the TA. If you have issues that should be kept confidential, then of course please do email the course lecturer, but otherwise use the forum - it is more efficient and it benefits everyone. For other questions, we have a bulletin-board type forum linked on the Learn menu as "Questions and Answers". Students can post questions and answers here too, but if the question relates to one of the course materials it is probably better to post it on NB.
||Hours & Minutes
|Main Exam Diet S1 (December)||2:00|
On completion of this course, the student will be able to:
- Explain the scope, goals and limits of machine learning, and the main sub-areas of the field.
- Describe the various techniques covered in the syllabus and where they fit within the structure of the discipline.
- Students should be able to critically compare, contrast and evaluate the different ML techniques in terms of their applicability to different Machine Learning problems.
- Given a data set and problem students should be able to use appropriate software to apply these techniques to the data set to solve the problem.
- Given appropriate data students should be able to use a systematic approach to conducting experimental investigations and assessing scientific hypotheses.
|Books that may be useful, but are not required:|
- Pattern Recognition and Machine Learning by C. Bishop
- Elements of Statistical Learning by Hastie, Tibshirani and Friedman
- Bayesian Reasoning and Machine Learning by D. Barber
- Machine Learning by T. Mitchell
- Reinforcement Learning by R. Sutton and A. Barto
- A Few Useful Things to Know about Machine Learning by P. Domingos
|Graduate Attributes and Skills
||Problem solving, Analytical thinking, Handling complexity and ambiguity, Independent learning and development.
||Practical Introduction to Data Science is recommended but not required.
1. Probability theory: Discrete and continuous univariate random variables. Expectation, variance. Univariate Gaussian distribution. Joint and conditional distributions.
2. Linear algebra: Vectors and matrices: definitions, addition, m atrix multiplication, matrix inversion. Eigenvectors, determinants quadratic forms.
3. Calculus: Functions of several variables. Partial differentiation. Multivariate maxima and minima.
4. Special functions: Log, exp
5. Geometry: Basics of lines, planes and hyperplanes. Coordinate geometry of circle, sphere, ellipse, ellipsoid and n - dimensional generalizatio ns.
6. Entropy: is useful, but will be covered in the lectures
Students should be familiar with programming in a modern object-oriented language, ideally Python which is the course language.
|Keywords||Distance Learning,Informatics,Machine Learning
|Course organiser||Dr Nigel Goddard
Tel: (0131 6)51 3091
|Course secretary||Ms Katey Lee
Tel: (0131 6)50 2701