Undergraduate Course: Machine Learning Practical (INFR11132)
|School||School of Informatics
||College||College of Science and Engineering
|Credit level (Normal year taken)||SCQF Level 11 (Year 4 Undergraduate)
||Availability||Available to all students
|Summary||This course is focused on the implementation and evaluation of machine learning systems, and is lab-based. Students who do this course will obtain experience in the design, implementation, training, and evaluation of machine learning systems.
This 20 credit course replaces INFR11119 Machine Learning Practical (10 credits).
The course will cover practical aspects of machine learning, and will focus on practical and experimental issues for a particular topic. Example topics on which the course could focus include:
* Artificial (deep) neural networks
* Reinforcement learning
* Gaussian processes
The course syllabus will thus be based on the particular focus for that year. For example, if the course focuses on artificial neural networks then following items would be covered:
* Feed-forward network architectures
* Optimisation of neural networks (stochastic gradient descent)
* Neural networks for classification
* Neural networks for regression
* Possible additional topics: Convolutional Neural Networks, Autoencoders, Restricted Boltzamnn Machines, Recurrent Neural Networks
MLP will be coursework-based, with lectures to support the additional material required to carry out the practical. Students who do this course will have experience in the design, implementation, training, and evaluation of machine learning systems.
Entry Requirements (not applicable to Visiting Students)
|Prohibited Combinations|| Students MUST NOT also be taking
Machine Learning Practical (INFR11119)
||Other requirements|| Familiarity with basic mathematics, including algebra and calculus is essential. A reasonable knowledge of computational, logical, geometric and set-theoretic concepts is assumed. Working knowledge of vectors and matrices is also necessary. A basic grasp of probability and partial differentiation, is also required. Students should have programming experience. Programming in a numerical language (Python/Numpy) will be required: previous experience in Python is not mandatory.
Information for Visiting Students
|High Demand Course?
Course Delivery Information
|Academic year 2016/17, Available to all students (SV1)
|Learning and Teaching activities (Further Info)
Lecture Hours 12,
Supervised Practical/Workshop/Studio Hours 20,
Programme Level Learning and Teaching Hours 4,
Directed Learning and Independent Learning Hours
|Assessment (Further Info)
|Additional Information (Assessment)
Assessment 1 - due week 6, Semester 1 - 10%
Assessment 2 - due week 10, Semester 1 - 25%
Assessment 3 - due week 3, Semester 2 - 25%
Assessment 4 - due week 8, Semester 2 - 40%
||Summative feedback will provided through marking of, and comments on, the assessed practicals. Detailed feedback from the first practical will be provided before the second practical deadline. All students will also be invited to sign-up to individual meetings to discuss the practical assessment. Formative feedback will provided via the lab sessions through discussion with the course lecturer and TA.
|No Exam Information
On completion of this course, the student will be able to:
- This course is focused on the implementation and evaluation of machine learning systems, and is lab-based. Students who do this course will obtain experience in the design, implementation, training, and evaluation of machine learning systems.
- Read technical papers, and explain their relevance to the chosen approach
- Design and carry out appropriate experiments, and explain the methodology involved
- Evaluate the resultant system
- Write a scholarly report, suitably structured and with supporting evidence
|Bishop: Pattern Recognition and Machine Learning;|
Murphy: Machine Learning - A Probabilistic Perspective.
Also specific material related to the course focus.
|Course organiser||Prof Stephen Renals
Tel: (0131 6)50 4589
|Course secretary||Mr Gregor Hall
Tel: (0131 6)50 5194
© Copyright 2016 The University of Edinburgh - 3 February 2017 4:27 am