Machine Learning for Domain Specialists
Module Overview
Dariush Hosseini
dariush.hosseini@ucl.ac.uk
Department of Computer Science
University College London
1 15
/ Aims
Aims
To introduce students to the basics of machine learning...
...While giving class-based examples of applications to areas of
domain specialisation.
2 15
/ Learning Outcomes
Learning Outcomes
This module has two main learning outcomes:
1 Understand elements of the fundamental concepts and
mathematical basis of machine learning.
2 Apply practical machine learning software in order to perform data
analysis tasks.
3 15
/ Information
Course Delivery
This year the content will be a mix of the synchronous and the
asynchronous
Note that the central hub for the details and delivery of all content
is Moodle.
4 15
/ Information
Course Delivery: Content
Lectures:
Asynchronous (i.e. pre-recorded)
Lecturecast recordings
Released on Moodle in advance of the lecture week
5 15
/ Information
Course Delivery: Content (cont.)
Classes:
Synchronous
Live, 2 hour, Blackboard Collaborate class (access via link on
Moodle)
Wednesdays, 11:00-13:00 & Fridays, 11:00-13:00
You should only attend one lab class per week
Activities released on Moodle in advance of the class week
6 15
/ Information
Course Delivery: Content (cont.)
Office Hour(s):
Synchronous (!)
Live MS Teams session (access via link on Moodle)
Mondays, 14:00-15:00 & Tuesdays, 11:00-12:00
Email:
Asynchronous
Please entitle any emails which you send to me ‘COMP0142’
7 15
/ Information
Moodle
8 15
/ Information
Course Contacts
Dariush Hosseini: dariush.hosseini@ucl.ac.uk;
Module Lead; Lectures
Ana Lawry Aguila: ana.aguila.18@ucl.ac.uk;
Doctoral T.A.; Classes
Manuel Birlo: manuel.birlo.18@ucl.ac.uk;
Doctoral T.A.; Classes
James Chapman: james.chapman.19@ucl.ac.uk;
Doctoral T.A.; Classes
Maria Del Mar Estarellas Garcia: maria.garcia.18@ucl.ac.uk;
Doctoral T.A.; Classes
Thomas Whitney: t.whitney@ucl.ac.uk;
Module Administrator
9 15
/ Information
Assessment
There are four units of assessment for this module:
Coursework 1 (20%)
Released [9th February 2021], hand-in [16th February 2021]
Coursework 2 (20%)
Released [24th March 2021], hand-in [31st March 2021]
Test 1 (Open Book)(24hrs) (30%)
Released [25th February 2021], hand-in [26th February 2021]
Test 2 (Open Book)(24hrs) (30%)
Released [25th March 2021], hand-in [26th March 2021]
10 15
/ Information
Assessment
Python will be used for practicals (both in class and in assessment)
24hr Open-Book Test submissions should be in PDF format
PDF’s should be prepared using LATEX(or MS Word + its equation
editor)
11 15
/ Information
Feedback
Courseworks
Individual: Grade and brief comments on question-by-question
performance
Open-Book Tests
Individual: Grade and brief comments on question-by-question
performance
Group: Model solutions class
12 15
/ Information
References
There are no formal texts which we will follow, however the following
provide useful background information for different elements of the
module:
Mathematics for Machine Learning, M. Deisenroth et al,
Cambridge
Introduction to Machine Learning, E. Alpaydin, MIT Press
Pattern Recognition & Machine Learning, C. Bishop, Springer
Hands-On Machine Learning with Scikit-Learn & Tensorflow, E.
Geron, O’Reilly
See the ‘Textbooks’ tab on Moodle for further details
13 15
/ Information
Mathematical Precursors
We will use elements of the following:
Linear algebra (vectors, matrices, eigenvectors / eigenvalues etc.)
Probability theory (random variables, expectation, variance,
conditional probabilities, Bayes rule etc.)
Statistics (sample statistics, maximum likelihood estimation etc.)
Calculus (derivatives, Taylor series, integrals etc.)
Some results from Convex Optimisation theory.
14 15
/ Information
Next Steps
Familiarise yourself with Moodle
In particular, check the ‘Announcements’...
...And follow the directions to the ‘Study Plan’ tab...
...Where you will find your first task list, entitled ‘0. Before Module
Commences’
Then check the ‘Announcements’ regularly - I’ll signal the arrival
of new content here
15 15
