| Unit name | Information Processing and the Brain (Teaching Unit) |
|---|---|
| Unit code | COMSM0075 |
| Credit points | 0 |
| Level of study | M/7 |
| Teaching block(s) |
Teaching Block 1 (weeks 1 - 12) |
| Unit director | Dr. Froudist-Walsh |
| Open unit status | Not open |
| Units you must take before you take this one (pre-requisite units) |
COMS10014 Mathematics for Computer Science A and COMS10013 Mathematics for Computer Science B or equivalent. A knowledge of Python or Julia. A basic knowledge of probability theory and of differential equations. |
| Units you must take alongside this one (co-requisite units) |
EITHER Assessment Units COMSM0073 Information Processing and the Brain (Exam assessment, 10 credits) OR COMSM0139 Information Processing and the Brain (Examination and Coursework assessment, 20 credits). Please note: COMSM0075 is the Teaching Unit for the Information Processing and the Brain option. Single Honours Computer Science and some Joint Honours students can choose to be assessed by either examination (10 credits, COMSM0073) or examination and coursework (20 credits, COMSM0139) by selecting the appropriate co-requisite assessment unit. Any other students that are permitted to take the Information Processing and the Brain option are assessed by examination (10 credits) and should be enrolled on the co-requisite exam assessment unit (COMSM0073). |
| Units you may not take alongside this one |
None. |
| School/department | School of Engineering Mathematics and Technology |
| Faculty | Faculty of Engineering |
Why is this unit important?
This unit explores information processing, statistical and deep learning in neuroscience. It starts out with an overview of information, statistical theory and the probabilistic brain before focusing on computational models of neural circuits and learning, including unsupervised, supervised and reinforcement learning, visual and auditory system, convolution and recurrent neural networks and the backpropagation algorithm in the brain. Finally, the unit explains how to relate these models to neural data.
Overall, the unit will enable students to understand how concepts from data science, machine learning and computational modelling are being used to probe one of the most challenging problems in science: how do our brains work
How does this unit fit into your programme of study
This is an optional unit that can be taken in Year 4.
An overview of content
In Information Processing and the Brain we learn about the ongoing conversation between neuroscience, machine learning and computer science: it is no coincidence that neural networks in machine learning are named after the neurons and the computational architecture of the brain has inspired both the detailed architecture and the broad ambition of computer science since computing machines were first conceived of; conversely, the algorithms and principles of computation discovered and formulated by computer science are a crucial framework for efforts to understand how the brain works. Insight into this conversation and these shared ideas comes through the examples of information theory, Bayesian fusion and a biomimetic approach to machine learning.
How will students, personally, be different as a result of the unit
The brilliant computer scientist Edsger Dijkstra is said to have pointed out that “Computer science is no more about computers than astronomy is about telescopes.” Students who have taken this unit will understand this, they will come to know that ideas about computation can be applied to the brain as well as to computers and that inspiration for novel algorithms can be found in nature as well as through machines.
Learning Outcomes
On successful completion of this unit, students will be able to:
When the unit is taken with the associated 20 credit option that includes coursework, students will also be able to:
Learning takes place in a a combination of synchronous and asynchronous sessions, including lectures, practical activities supported by drop-in sessions, problem sheets and self-directed exercises. If taken with coursework, the unit also provides weekly coursework support sessions.
Tasks which help you learn and prepare you for summative tasks (formative):
Teaching will take place over Weeks 1-7, with coursework support in weeks 9-11 and for students assessed by examination, consolidation and revision sessions in Weeks 12.
The exam will test knowledge of the key concepts taught in the unit along with an ability to perform calculations using the tools discussed; the formative worksheets and tutorial tasks will support this.
The course work will involve an implementation task, so familiarity with coding and with deep learning libraries, will be important; some support for this will come from the tutorial tasks.
Tasks which count towards your unit mark (summative):
2 hour exam (10 credits: COMSM0073 – 100%, COMSM0139 – 50%) for all students covering prepared and selected topics (also see interactive intended learning outcomes).
In addition, students taking COMSM0139 will also take a coursework in weeks 9-11 (50%, equiv. to 10 credits).
When assessment does not go to plan
Students will retake relevant assessments in a like-for-like fashion in accordance with the University rules and regulations
If this unit has a Resource List, you will normally find a link to it in the Blackboard area for the unit. Sometimes there will be a separate link for each weekly topic.
If you are unable to access a list through Blackboard, you can also find it via the Resource Lists homepage. Search for the list by the unit name or code (e.g. COMSM0075).
How much time the unit requires
Each credit equates to 10 hours of total student input. For example a 20 credit unit will take you 200 hours
of study to complete. Your total learning time is made up of contact time, directed learning tasks,
independent learning and assessment activity.
See the University Workload statement relating to this unit for more information.
Assessment
The Board of Examiners will consider all cases where students have failed or not completed the assessments required for credit.
The Board considers each student's outcomes across all the units which contribute to each year's programme of study. For appropriate assessments, if you have self-certificated your absence, you will normally be required to complete it the next time it runs (for assessments at the end of TB1 and TB2 this is usually in the next re-assessment period).
The Board of Examiners will take into account any exceptional circumstances and operates
within the Regulations and Code of Practice for Taught Programmes.
