- Student Records
Programme & Unit Catalogues

CM50265: Machine learning 2

Follow this link for further information on academic years Academic Year: 2018/9
Further information on owning departmentsOwning Department/School: Department of Computer Science
Further information on credits Credits: 6      [equivalent to 12 CATS credits]
Further information on notional study hours Notional Study Hours: 120
Further information on unit levels Level: Masters UG & PG (FHEQ level 7)
Further information on teaching periods Period:
Semester 2
Further information on unit assessment Assessment Summary: CW 100%
Further information on unit assessment Assessment Detail:
  • Written Report + Presentation (CW 40%)
  • Completed Lab Reports (CW 60%)
Further information on supplementary assessment Supplementary Assessment:
Like-for-like reassessment (where allowed by programme regulations)
Further information on requisites Requisites:
Further information on descriptions Description: Aims:
This unit covers the breadth of machine learning topics as well as providing detailed treatment of advanced methods that are representative of the different categories of ML approaches.

Learning Outcomes:
At the end of this unit, students will be able to:
* Demonstrate a systematic knowledge of state-of-the-art ML approaches and an awareness of the latest ongoing research in the field
* Develop and evaluate critically advanced ML models for real-world problems
* Identify and implement appropriate and original algorithms to perform inference
* Make predictions from models and account for uncertainty

Intellectual skills:
* Demonstrate an advanced conceptual understanding of ML modelling (T, F, A)
* Critical analysis of advanced models and algorithms (T, F, A)
Practical skills:
* Produce practical implementations of advanced ML algorithms (T, F, A)
* Evaluate and critique algorithms on complex data (T, F, A)
Transferable skills:
* Numerical programming and independent learning (F, A)
* Technical report writing and presentation skills (F, A)

Topics covered will normally include: Bayesian approaches to ML, graphical models (e.g. Markov random fields), Bayesian non-parametric models (e.g. Gaussian processes), deep learning (e.g. neural networks), time series (e.g. hidden Markov models), sparse models (e.g. compressed sensing), and unsupervised learning (e.g. density estimation).
Further information on programme availabilityProgramme availability:

CM50265 is Compulsory on the following programmes:

Department of Computer Science