Labs (starting 2nd Feb). To tell what group you're in look in your Outlook calendar. You will see one of the following two slots:
Group 1: Thursday 4-5pm in MVB 2.11
Group 2: Thursday 5-6pm in MVB 2.11
Strikes: Laurence is on strike for three Thursdays (9th Feb, 16th Feb and 23rd Feb). There will therefore be no lectures on those days. The Monday lectures + Thursday labs are still going ahead.
Revision online Teams QA sessions:
Laurence: Thursday 27th April 1pm
Majid: Thursday 4th May 1pm
Lecture recordings:
All lecture recordings are present on the Re/Play system in BlackBoard. (Click on Re/Play on the left menu bar on the BB course webpage). Note that lectures should appear automatically, but may take a few hours to turn up in Re/Play.
Labs:
The labs are starting on Feb 2nd, so there will be no lab on 26th Jan.
The labs come with exercises as Python notebook. A new set of exercises will be released every two weeks. (So there will be a new notebook on 2nd Feb and Feb 16th but not 9th Feb).
Material in the labs may appear in the exam.
The labs are the primary route for feedback on all aspects of the course, including lectures, any question sheets and exams, not just the labs!!!!
The lab exercises will be released in the /labs/ folder.
Lab 4 (just released) is the last lab.
Other information:
The Teams Team is "COMS20011: Data-Driven Computer Science 2022/23". You should have access already through the "Teams" panel. If not, please get in touch with the school office (coms-info@bristol.ac.uk)!
Routes for feedback:
TA led sessions on Thursday 4-5 (group 1) or 5-6 (group 2) (you should have one of these slots in your calendar). You can ask about all aspects of the course lectures, labs and exams. We have a room for these (MVB 2.11), and some support will be available in the room. We may also have support available online. The first lab session is on 2nd Feb (there will be no session on Jan 26th).
You can ask questions on the Teams General Channel.
We may use a few of the lecture slots as online QA slots (there will be an email beforehand about this).
Exam info:
The course is assessed 100% by exam.
The exam is a 20 question, 2 hour, in-person multiple-choice exam.
The exam does require a calculator. Advise from faculty from TB1 on calculators was "The faculty recommended calculator is a Casio FX-83GT X. The faculty no longer requires students to obtain a seal for your calculator. Your calculator will be visually checked by an invigilator during each exam. Please be advised that the use of a programmable calculator will be treated as an examination offence (and is likely to incur a penalty under the University Assessment Regulations). For students who do not own or are unable to obtain a non-programmable calculator prior to their exam please email feng-ugadmin@bristol.ac.uk to obtain further advice." (If this changes, we'll all be sent an email from faculty).
The exam does not in the end have any Python (we were thinking about putting Python in the exam, but it ended up being difficult to be certain what everyone knows given that Python is only used in the labs).
If you have any questions regarding alternative exam arrangements, please get in touch with the school office (coms-info@bristol.ac.uk): we don't have any involvement in this.
We will release past papers towards the end of Majid's teaching.
There is a formula sheet in the exam (which is currently in the Teams channel).
You are allowed to write on the exam paper, and we have a number of sheets at the back of the exam paper that are explicitly for workings out! (Apparently, the invigilators aren't allowed to give you extra paper for workings out in MCQ exams, for some reason that nobody seems to know...)
We have rejigged the course content a bit this year, so some questions are no longer relevant. These questions are in the "Questions to ignore" column.
The 20/21 exam was exceptionally shorter due to the pandemic. This year's exam will have 20 questions, like the 21/22 exam.
Alternative resources
Important: these are not pre-requisites! The course material should be fully self-contained. But some of this may be useful if you want an alternative presentations of some of the material and/or if you have a general interest in data-science. Feel free to raise an issue/pull-request if you have recommendations for other resources.
Probabilistic machine learning (relevant for Laurence's part of the course):
Probabilistic Machine Learning: An Introductionpdf (Parts I - III are most relevant. Obviously that's quite a bit, ranging from fundamentals to deep learning. But different people will find different bits most relevant).
Probability and statistics
A Modern Introduction to Probability and Statistics, Understanding Why and How (Dekking et al.)