This unit covers quite a lot of content; essentially a first course in probability, statistics and machine learning rolled up into one. It seems that the teaching team have improved the subject significantly from when the other reviews were written, as while I think there are things that can be improved, it was run quite well. A highlight would be the amount and quality of communication from staff, along with a large amount of practise resources. The assignment was a mixture of standard maths questions and a Kaggle competition which was quite fun. There were weekly "quizzes", which were technically optional but had bonus marks associated with them, which were a good incentive to practise the content regularly. Tutorials/labs were geared more towards application of content using R. Both the mid sem and final exam were fair, with the final exam being straightforward. Overall it was an alright core subject for the Master of AI/DS degree, with the content itself just being boring but necessary to cover.

Wish I could give it 0 stars

avoid at all costs

As a graduate student with working experience I know that Statistics and Mathematics are difficult subjects to learn and we gain a lot from strong lecturers who explain the material with great slides and lecturing style. As a benchmark of quality, Monash's MAT9004 2018 S1 is a testament to a well-considered curriculum and carefully structured lectures and lecture slides which were rehearsed before hand. Monash's FIT5197 2018 S2 is the opposite, with lecture notes clearly developed by someone else and being used by current lecturers. Granted MAT9004 is a foundational unit but FIT5197 as an intermediate unit lacks any of the polish found in MAT9004. The second half's Lecturer's lack of preparation in terms of practicing what that person was going to say is very, very clear with mistakes in terminology used during the lecture which were spotted while reviewing the recordings and other times you will find lecturer statements either vague or at worst, misleading. In other instances, the younger lecturer of the two has included tangential information when introducing a new topic which offer more to confuse than to enhance knowledge. And the amount of "uhs" and "ums" per sentence are at the level of a junior white collar staff presenting to his seniors in his first year. And when he reaches points within his lecture where he has to explain a complex topic it comes out slow and constipated as though he did not prepare his definition before hand and was simply "winging it". E.g in Lecture Week 9, I spent 30 minutes figuring out 9 minutes of lecture presented because the lecture followed no discernible logical flow. This commonly occurred in lectures especially with regards to the second lecturer. The main benefit (which raises this from a 1 star course to a 2 star course) you will get out of this course are not the lectures but the tutorial questions and their worked solutions. Tutorial questions are well considered, you will learn the most from reviewing the lectures once, diving into the tutorials and figuring things out by doing because the lectures are sub-par at explaining a lot of things. The alexandria modules: The first module was poorly written by someone who is no longer with the faculty with spelling errors and a general poor approach to writing style and structure. Quiz Assessment Review (Later) Assignments Assessment Review (Later)