G5BAIM Artificial Intelligence Methods - Course Feedback 1999/00

Artificial Intelligence Methods (G5BAIM)
Course Feedback - Academic Year 1999/00

This course is run at Nottingham University. It is a second/third year option. This page summarises the feedback from the students that attended the course. All comments are listed. A response from the lecturer is also given and at the end there are some notes with regards to the examination.

The lecturer is Graham Kendall. Feel free to email me or visit my home page.

The home page for the course (including a full set of course handouts) can be found here.

Comments from Course Feedback Forms

I think he is a brilliant lecturer. If he had been teaching me in the first year I may not have dropped computer science in the first place
Variety in presentation (powerpoint, slides, notes etc.)
Good web site - simple and efficient
Good coursework - really interesting and relevant
Slides were very good, supported with comprehensive notes
Good Presentation
Approachable
Lectures at 9am were rubbish. I attended none of them as I did not have any other lectures and as notes were on the web there was no incentive to attend
Slides and notes were good
Obviously knew what he was talking about
Enthusiastic about the subject and used planty of interesting examples
Slow down the lecture pace slightly
Enthusiastic and clear examples
Humour retained interest
Bigger fonts for some of the powerpoint slides
Very Good notes
Well structured lectures
Good use of powerpoint
Making all notes available on the web is a good thing
Straucture of course was clearly laid out from the outset
Stop repeating himself
He claimed there was no mths in the module, yet there was a fair amount popping up in the lectures
His lecture notes were up to date
The coursework set for this year was very difficult. I would have liked the lecturer to set three smaller pieces of coursework
Interesting lecturer and down to earth
The coursework was the most effective teaching aid
I enjoyed the course
The lecturer is very approachable
Multiple methods of teacjing (slides, OHP's, spreadhsheets) is good
Good speaker
Interesting - simple (most of the time) is conveying concepts
The lecturer appears to have a good knowledge of the subject area
Sometimes the lecturer explained something and then went onto a powerpoint slide which said the same thing that we had just been told. This was very dull
Clear and good pace
Excellent handouts and overheads
I think it was unfair to ask people at a 9am lecture which one should be dropped - the "other" people would have been unrepresented there
I felt the course went too fast and 2 lectures a week would have given me time to understand the course as it went along - as it was I got pretty lost
Entertaining
The course was just copied out of a a textbook - it might as well have been a correspondence course
The slides were the most effective teaching method
Use of AV (audio visual) were the most effective teaching method
The lecturer is very punctual!
The lecture notes are very clear
Generally, a good lecturer
The lecturer likes his subject
There was too much content
The course could do with some exercises
There are too may 09:00 lectures
The notes being available on the web is the most effective teaching aid
Interesting slides
Use of laser pointer
Red Dwarf theme
The lecturer mumbles to himself
Good Pace
Review past exam papers would be useful
Geast lecturers would be useful
The lecturer really prepared well for the lectures
Give answers of the exam!!
The lecturers notes are very good
The lecturer is helpful and punctual
Very good notes
Use of powerpoint is effective
Comprehensive lecture notes
The lecturer is approachable for question (direct or EMAIL)
Good use of audio-visual equipment
Good examples
Clear references to other pertinent material
Provide more "hand-on" opportunites in lectures for learning algorithms and non-assessed coursework
The lecturers enthusiasm and clear explanations of occasionally complex algorithms was the most effective teaching aid
There were occasional errors in the slides
On the whole it was good
The most effective teaching aid is the lecturers enthusiasm and his humour
Change some of the colours on the powerpoint slides
Give practical examples of various techniques
The lecturer got everything across well
Nice use of powerpoint
Maybe a few more interactive bits
Good use of electronic media, which aided the course
Other lecturers should takes notes from this lecturer on how a lecture should be structured and presented
I would like the handouts in the lecture, not off the web, so that I do not have to unzip them

Total Questionnaires Returned = 63

Number of students who sat exam = 119

Lecturers Response
Overall I am plesaed with this course feedback. Next year, this course may change as it may be split into two modules. If this is done I will take the opportunity to update my powerpoint slides and try to develop the areas where I have been criticised (e.g. more interaction, more examples, more hands on). Examination Report

General

118 people took the exam for this course. 10 people failed to hand in the coursework.
The figures for the number of candidates who attempted the questions are based on those questions that contributed towards their marks. That is, if the student attempted five questions, only four are counted in this report.
The overall average for this course was slightly above what was expected.

Coursework

The coursework involved writing various search algorithms to solve the 8-puzzle problem.
From the feedback I received the coursework was well received and most people found it challenging but an enjoyable assignment.
The overall average for the coursework was below the expected average but, if the 10 people who did not hand in their assignment are excluded from the calculation then the average is very close to the expected value.

Question 1

This question was attempted by 110 candidates. The question was similar to previous exam questions (A* algorithm) and its use had been explained at various times throughout the lectures.
The question achieved an above average mark, although many students found difficulty in producing the correct search tree and stating the correct route.

Question 2

This question was attempted by 110 candidates. It mainly involved genetic algorithms as well as considering other population based approaches. The students were divided between those that could apply the algorithms correctly and those that really had no idea.
The second part of the question was not so well answered with not many students giving their own ideas, rather they quoted material from the lectures.
The question achieved an above average mark.

Question 3

This question was attempted by 67 candidates. The question asked the students to consider two neighbourhood search algorithms (hill climbing and simulated annealing).
In general, the students were able to describe the two search algorithms but found difficulty in describing the relationship between the two, without giving two separate algorithms.
The question also asked the student to show an example of how likely simulated annealing is to accept a worse move. This was, in general, poorly answered.
This question achieved a below average mark.

Question 4

This question was attempted by 95 candidates. It asked the students to describe the Turing Test and The Chinese Room Experiment and then comment on the issues raised by these two experiments.
The students gave good, reasoned descriptions and arguments for these topics and the question achieved an above average mark.

Question 5

This question was attempted by 10 candidates. This question asked the students to give their opinion as to what constitutes artificial life and the problems it would pose. In addition, the students were asked to describe their ideas as to how a computer program could learn how to play a card game (blackjack).
The low number of students who attempted this question, I assume, shows they thought it was a difficult question.
This is probably the case as it achieved the lowest average mark of all the questions.

Question 6

This question was attempted by 83 candidates. The question asked the students to state what functions could be learnt by a perceptron and then comment on how two types of perceptrons (but identical in operation) could be built.
This question is very similar to questions from previous exams. This is probably one reason why it achieved the highest average mark and was generally well answered by those attempting it.