skip to content

Department of Computer Science and Technology

 
Principal lecturer: 
Other lecturers: 
Carl Rasmussen
Students: 
MPhil ACS, Part III
Term: 
Michaelmas term
Course code: 
LE49
Prerequisites: 
Strong background in statistics, calculus and linear algebra, courses in statistical signal processing will be required. More detail of prerequisites should be reviewed on the Engineering Department website: http://mlg.eng.cam.ac.uk/teaching/4f13/1920/
Hours: 
17
Class limit: 
18

Further information

This module is borrowed from the Department of Engineering and some of the lectures are given at the Trumpington Street site during Michaelmas Term. Students wishing to take this module should note that the Department of Engineering is about 2 miles from the Computer Laboratory.

Syllabus

Lectures

  • Students will take the first ten hours of lectures over at the Department of Engineering - Please refer to the Engineering Course 4f13 webpage for details of the content.
  • Two 1.5 hour lectures (one near the beginning of the term, one closer to the middle) will be given to preview what the forthcoming lectures will be covering, and prime students on the notation.
  • Four 1 hour lectures on "Neural networks as probabilistic models"

Assessment

There are four pieces of coursework. The first three are structured exercises designed to reinforce the lectures. The fourth is an open-ended investigation of a topic that you chose from a small list, drawing on the main themes of the lecture course.

  1. Gaussian processes exercise (10%, due in Michaelmas term)
  2. Probabilistic ranking exercise (10%, due in Michaelmas term)
  3. Topic modelling exercise (10%, due in Michaelmas term)
  4. Investigative project (70%, due beginning of Lent term)

The investigative project should be written up in the style of a NIPS or ICML conference paper, 8 pages plus one for references.

Further Information

Due to COVID-19, the method of teaching for this module will be adjusted to cater for physical distancing and students who are working remotely. We will confirm precisely how the module will be taught closer to the start of term.