Lifelong Multi-output Machine Learning

Degree type


Closing date

27 March 2023


Hobart, Launceston

Citizenship requirement


About the research project

Prediction is one of the most common and important tasks in artificial intelligence (AI). With the emergence of deep learning, the AI community has achieved state-of-the-art prediction results in an array of applications, from object detection to medical image classification. Currently, most prediction tasks are focusing on a single output, e.g. human identity or disease type from medical images, and a single dataset. Although there exist multi-label approaches to deal with the prediction of multiple nonexclusive labels, it is still a challenging problem for many real-life applications with different sets of constrained labels. Moreover, most of the current methods deal with fixed sets of classes while these classes can change when new data is available. In this project, we will investigate effective solutions to address the life-long multi-output prediction problem. In particular, we will develop learning models and strategies to represent the relationship between the labels and to allow continual learning where new classes can be included seamlessly. For the empirical study, we will evaluate the effectiveness of our approaches on object classification. We will also showcase the usefulness of the solutions on plant pathology where we can incrementally build up a model from different datasets with different plant species and different disease types.

Primary Supervisor

Meet Dr Son Tran


Applicants will be considered for a Research Training Program (RTP) scholarship or Tasmania Graduate Research Scholarship (TGRS) which, if successful, provides:

  • a living allowance stipend of $31,500 per annum (2023 rate, indexed annually) for 3.5 years
  • a relocation allowance of up to $2,000
  • a tuition fees offset covering the cost of tuition fees for up to four years (domestic applicants only)

If successful, international applicants will receive a University of Tasmania Fees Offset for up to four years.

As part of the application process you may indicate if you do not wish to be considered for scholarship funding.


Applicants should review the Higher Degree by Research minimum entry requirements.

Additional eligibility criteria specific to this project/scholarship:

  • Applicants must be able to undertake the project on-campus

Selection Criteria

The project is competitively assessed and awarded.  Selection is based on academic merit and suitability to the project as determined by the College.

Additional essential selection criteria specific to this project:

  • Background in ICT or Computer Science
  • Good programming skills
  • Good communication skills

Additional desirable selection criteria specific to this project:

  • Have experience with deep learning techniques

Application process

There is a three-step application process:

  1. Select your project, and check you meet the eligibility and selection criteria;
  2. Contact the Primary Supervisor, Dr Son Tran to discuss your suitability and the project's requirements; and
  3. Submit an application by the closing date listed above.
    • Copy and paste the title of the project from this advertisement into your application. If you don’t correctly do this your application may be rejected.
    • As part of your application, you will be required to submit a covering letter, a CV including 2 x referees and your project research proposal.

Following the application closing date applications will be assessed within the College. Applicants should expect to receive notification of the outcome by email by the advertised outcome date.

Apply now Explore other projects

Why the University of Tasmania?

Worldwide reputation for research excellence

Quality supervision and support

Tasmania offers a unique study lifestyle experience