Handbook home
Real and Artificial Neural Networks (NEUR30006)
Undergraduate level 3Points: 12.5On Campus (Parkville)
About this subject
- Overview
- Eligibility and requirements
- Assessment
- Dates and times
- Further information
- Timetable(opens in new window)
Contact information
Semester 2
Peter Kitchener
Email: pkitc@unimelb.edu.au
Overview
Availability | Semester 2 |
---|---|
Fees | Look up fees |
The analysis of real neural networks and the construction of artificial neural networks afford mutually synergistic technologies with broad application within and beyond neuroscience. Artificial neural networks, and other machine learning methods, have found numerous applications in analysis and modelling, and have produced insights into numerous complex phenomena (and generated huge economic value). Such technologies can also be used to gain insights into the biological systems that inspired their creation: we will explore how learning is instantiated in artificial and biological neural networks.
The subject aims to provide foundation skills for those who may wish to peruse neuroscience - or any research or work environment that involves the creation or capture, and analysis, of complex data. Students will gain experience with digital signals and digital signal processing (whether those signals are related to images, molecular data, connectomes, or electrophysiological recordings), and will learn how to conceptualise and implement approaches to modelling data by constructing an artificial neural network using the Python programming language.
Intended learning outcomes
On completion of this subject students should be able to:
- Program in Python using Jupyter notebook.
- Build an artificial neural network to perform a learning task on a large dataset.
- Visualise and evaluate the performance of the artificial neural networks they construct.
- Understand the nature of data, noise, and computational models.
Generic skills
On completion of this subject students should have developed skills in:
- Independent critical thought.
- Understanding different experimental approaches and modelling approaches to problems.
- Analysing complex scientific problems and interpreting experimental findings.
- Understanding the interrelationship of ideas and technologies in multi-disciplinary science.
Last updated: 11 April 2024
Eligibility and requirements
Prerequisites
EITHER: NEUR30003 Principles of Neuroscience OR NEUR30002 Neurophysiology: Neurons and Circuits.
Code | Name | Teaching period | Credit Points |
---|---|---|---|
NEUR30002 | Neurophysiology: Neurons and Circuits | Semester 1 (On Campus - Parkville) |
12.5 |
Code | Name | Teaching period | Credit Points |
---|---|---|---|
NEUR30003 | Principles of Neuroscience | Semester 1 (On Campus - Parkville) |
12.5 |
Corequisites
None
Non-allowed subjects
None
Recommended background knowledge
High School-level differential calculus and matrix operations.
Inherent requirements (core participation requirements)
The University of Melbourne is committed to providing students with reasonable adjustments to assessment and participation under the Disability Standards for Education (2005), and the Assessment and Results Policy (MPF1326). Students are expected to meet the core participation requirements for their course. These can be viewed under Entry and Participation Requirements for the course outlines in the Handbook.
Further details on how to seek academic adjustments can be found on the Student Equity and Disability Support website: http://services.unimelb.edu.au/student-equity/home
Last updated: 11 April 2024
Assessment
Description | Timing | Percentage |
---|---|---|
Four 15-minute quizzes in weeks 2, 4, 6 & 8. (5% each).
| Throughout the semester | 20% |
Mid-semester test
| Mid semester | 20% |
Written report
| During the examination period | 60% |
Last updated: 11 April 2024
Dates & times
- Semester 2
Principal coordinator Peter Kitchener Mode of delivery On Campus (Parkville) Contact hours 1-hour seminar, 1-hour tutorial and 1-hour workshop per week. Total: 36 hours. Total time commitment 170 hours Teaching period 29 July 2019 to 27 October 2019 Last self-enrol date 9 August 2019 Census date 31 August 2019 Last date to withdraw without fail 27 September 2019 Assessment period ends 22 November 2019 Semester 2 contact information
Peter Kitchener
Email: pkitc@unimelb.edu.au
Time commitment details
36 contact hours with 134 hours of independent work on an artificial neural network.
Last updated: 11 April 2024
Further information
- Texts
Prescribed texts
There are no specifically prescribed or recommended texts for this subject.
- Breadth options
This subject is available as breadth in the following courses:
- Available to Study Abroad and/or Study Exchange Students
This subject is available to students studying at the University from eligible overseas institutions on exchange and study abroad. Students are required to satisfy any listed requirements, such as pre- and co-requisites, for enrolment in the subject.
Last updated: 11 April 2024