Associate Professor Marcus Gallagher
Associate Professor

Marcus Gallagher

Email: 
Phone: 
+61 7 336 56197

Background

Marcus Gallagher is an Associate Professor in the Artificial Intelligence Group in the School of Information Technology and Electrical Engineering. His research interests are in artificial intelligence, including optimisation and machine learning. He is particularly interested in understanding the relationship between algorithm performance and problem structure via benchmarking. My work includes cross-disciplinary collaborations and real-world applications of AI techniques.

Dr Gallagher received his BCompSc and GradDipSc from the University of New England, Australia in 1994 and 1995 respectively, and his PhD in 2000 from the University of Queensland, Australia. He also completed a GradCert (Higher Education) in 2010.

Availability

Associate Professor Marcus Gallagher is:
Available for supervision
Media expert

Fields of research

Biomedical and Clinical Sciences Health Sciences Information and Computing Sciences Mathematical Sciences Numerical and computational mathematics Optimisation Statistics Theory of computation

Qualifications

  • Bachelor of Computer Science, University of New England Australia
  • Postgraduate Diploma, University of New England Australia
  • Doctor of Philosophy, The University of Queensland

Search Professor Marcus Gallagher’s works on UQ eSpace

146 works between 1990 and 2024
All (146) Journal Article (47) Book Chapter (1) Conference Publication (92) Book (1) Other Outputs (3) Edited Outputs (2)

21 - 40 of 146 works

2020

Journal Article

Predicting alcohol dependence treatment outcomes: A prospective comparative study of clinical psychologists vs ‘trained’ machine learning models

Symons, Martyn, Feeney, Gerald F. X., Gallagher, Marcus R., Young, Ross Mc D. and Connor, Jason P. (2020). Predicting alcohol dependence treatment outcomes: A prospective comparative study of clinical psychologists vs ‘trained’ machine learning models. Addiction, 115 (11) add.15038, 2164-2175. doi: 10.1111/add.15038

Predicting alcohol dependence treatment outcomes: A prospective comparative study of clinical psychologists vs ‘trained’ machine learning models

2020

Conference Publication

A novel mutation operator for variable length algorithms

Van Ryt, Saskia, Gallagher, Marcus and Wood, Ian (2020). A novel mutation operator for variable length algorithms. AI 2020: Advances in Artificial Intelligence: 33rd Australasian Joint Conference, Canberra, ACT, Australia, 29 - 30 November 2020. Heidelberg, Germany: Springer. doi: 10.1007/978-3-030-64984-5_14

A novel mutation operator for variable length algorithms

2020

Conference Publication

An Implementation and Experimental Evaluation of a Modularity Explicit Encoding Method for Neuroevolution on Complex Learning Tasks

Qiao, Yukai and Gallagher, Marcus (2020). An Implementation and Experimental Evaluation of a Modularity Explicit Encoding Method for Neuroevolution on Complex Learning Tasks. 33rd Australasian Joint Conference, AI 2020, Canberra, ACT Australia, 29–30 November 2020. Heidelberg, Germany: Springer. doi: 10.1007/978-3-030-64984-5_11

An Implementation and Experimental Evaluation of a Modularity Explicit Encoding Method for Neuroevolution on Complex Learning Tasks

2020

Book

AI 2020: advances in artificial intelligence

Marcus Gallagher, Nour Moustafa and Erandi Lakshika eds. (2020). AI 2020: advances in artificial intelligence. Lecture Notes in Computer Science, Heidelberg, Germany: Springer. doi: 10.1007/978-3-030-64984-5

AI 2020: advances in artificial intelligence

2020

Conference Publication

Fitness landscape features and reward shaping in reinforcement learning policy spaces

du Preez-Wilkinson, Nathaniel and Gallagher, Marcus (2020). Fitness landscape features and reward shaping in reinforcement learning policy spaces. Parallel Problem Solving from Nature – PPSN XVI, Leiden, The Netherlands, 5 - 9 September 2020. Heidelberg, Germany: Springer. doi: 10.1007/978-3-030-58115-2_35

Fitness landscape features and reward shaping in reinforcement learning policy spaces

2019

Journal Article

Network analysis and visualisation of opioid prescribing data

Hu, Xuelei, Gallagher, Marcus, Loveday, William, Dev, Abhilash and Connor, Jason P. (2019). Network analysis and visualisation of opioid prescribing data. IEEE Journal of Biomedical and Health Informatics, 24 (5) 8822723, 1-9. doi: 10.1109/jbhi.2019.2939028

Network analysis and visualisation of opioid prescribing data

2019

Conference Publication

Reversible jump probabilistic programming

Roberts, David A., Gallagher, Marcus and Taimre, Thomas (2019). Reversible jump probabilistic programming. The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019), Naha, Okinawa, Japan, 16 - 18 April 2019. Brookline, MA, United States: ML Research Press.

Reversible jump probabilistic programming

2019

Journal Article

Machine learning vs addiction therapists: a pilot study predicting alcohol dependence treatment outcome from patient data in behavior therapy with adjunctive medication

Symons, Martyn, Feeney, Gerald F.X., Gallagher, Marcus R., Young, Ross McD. and Connor, Jason P. (2019). Machine learning vs addiction therapists: a pilot study predicting alcohol dependence treatment outcome from patient data in behavior therapy with adjunctive medication. Journal of Substance Abuse Treatment, 99, 156-162. doi: 10.1016/j.jsat.2019.01.020

Machine learning vs addiction therapists: a pilot study predicting alcohol dependence treatment outcome from patient data in behavior therapy with adjunctive medication

2019

Journal Article

Quantitative measure of nonconvexity for black-box continuous functions

Tamura, Kenichi and Gallagher, Marcus (2019). Quantitative measure of nonconvexity for black-box continuous functions. Information Sciences, 476, 64-82. doi: 10.1016/j.ins.2018.10.009

Quantitative measure of nonconvexity for black-box continuous functions

2019

Conference Publication

Fitness landscape analysis in data-driven optimization: An investigation of clustering problems

Gallagher, Marcus (2019). Fitness landscape analysis in data-driven optimization: An investigation of clustering problems. IEEE Congress on Evolutionary Computation (IEEE CEC), Wellington, New Zealand, 10-13 June, 2019. Piscataway, NJ, United States: Institute of Electrical and Electronics Engineers. doi: 10.1109/CEC.2019.8790323

Fitness landscape analysis in data-driven optimization: An investigation of clustering problems

2019

Conference Publication

Exchangeability and kernel invariance in trained MLPs

Tsuchida, Russell, Roosta, Fred and Gallagher, Marcus (2019). Exchangeability and kernel invariance in trained MLPs. Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19, Macao, China, 10-16 August 2019. Marina del Rey, CA USA: International Joint Conferences on Artificial Intelligence. doi: 10.24963/ijcai.2019/498

Exchangeability and kernel invariance in trained MLPs

2019

Conference Publication

Exploring the MLDA benchmark on the Nevergrad platform

Rapin, Jeremy, Gallagher, Marcus, Kerschke, Pascal, Preuss, Mike and Teytaud, Olivier (2019). Exploring the MLDA benchmark on the Nevergrad platform. 2019 Genetic and Evolutionary Computation Conference, GECCO 2019, Prague, Czech Republic, 13 - 17 July 2019. New York, New York, USA: Association for Computing Machinery, Inc. doi: 10.1145/3319619.3326830

Exploring the MLDA benchmark on the Nevergrad platform

2018

Journal Article

Direct feature evaluation in black-box optimization using problem transformations

Saleem, Sobia, Gallagher, Marcus and Wood, Ian (2018). Direct feature evaluation in black-box optimization using problem transformations. Evolutionary Computation, 27 (1), 75-98. doi: 10.1162/evco_a_00247

Direct feature evaluation in black-box optimization using problem transformations

2018

Conference Publication

A model-based framework for black-box problem comparison using gaussian processes

Saleem, Sobia, Gallagher, Marcus and Wood, Ian (2018). A model-based framework for black-box problem comparison using gaussian processes. 15th International Conference on Parallel Problem Solving from Nature, PPSN 2018, Coimbra, Portugal, 8-12 September 2018. Cham, Switzerland: Springer Verlag. doi: 10.1007/978-3-319-99259-4_23

A model-based framework for black-box problem comparison using gaussian processes

2018

Conference Publication

Flood-fill Q-learning updates for learning redundant policies in order to interact with a computer screen by clicking

du Preez-Wilkinson, Nathaniel, Gallagher, Marcus and Hu, Xuelei (2018). Flood-fill Q-learning updates for learning redundant policies in order to interact with a computer screen by clicking. 31st Australasian Joint Conference on Artificial Intelligence, AI 2018, Wellington,, December 11, 2018-December 14, 2018. Germany: Springer Verlag. doi: 10.1007/978-3-030-03991-2_49

Flood-fill Q-learning updates for learning redundant policies in order to interact with a computer screen by clicking

2018

Conference Publication

Invariance of weight distributions in rectified MLPs

Tsuchida, Russell, Roosta-Khorasani, Farbod and Gallagher, Marcus (2018). Invariance of weight distributions in rectified MLPs. 35th International Conference on Machine Learning, Stockholm, Sweden, 10-15 July 2018. Cambridge, MA, United States: M I T Press.

Invariance of weight distributions in rectified MLPs

2018

Conference Publication

Intra-task curriculum learning for faster reinforcement learning in video games

du Preez-Wilkinson, Nathaniel, Gallagher, Marcus and Hu, Xuelei (2018). Intra-task curriculum learning for faster reinforcement learning in video games. 31st Australasian Joint Conference on Artificial Intelligence (AI 2018), Wellington, New Zealand, 11-14 December 2018. Cham, Switzerland: Springer. doi: 10.1007/978-3-030-03991-2_6

Intra-task curriculum learning for faster reinforcement learning in video games

2017

Journal Article

Parallel evolutionary algorithm for single and multi-objective optimisation: Differential evolution and constraints handling

Pedroso, Dorival M., Bonyadi, Mohammad Reza and Gallagher, Marcus (2017). Parallel evolutionary algorithm for single and multi-objective optimisation: Differential evolution and constraints handling. Applied Soft Computing, 61, 995-1012. doi: 10.1016/j.asoc.2017.09.006

Parallel evolutionary algorithm for single and multi-objective optimisation: Differential evolution and constraints handling

2017

Journal Article

Multiple community energy storage planning in distribution networks using a cost-benefit analysis

Sardi, Junainah, Mithulananthan, N., Gallagher, M. and Hung, Duong Quoc (2017). Multiple community energy storage planning in distribution networks using a cost-benefit analysis. Applied Energy, 190, 453-463. doi: 10.1016/j.apenergy.2016.12.144

Multiple community energy storage planning in distribution networks using a cost-benefit analysis

2017

Journal Article

Use of freely available datasets and machine learning methods in predicting deforestation

Mayfield, Helen, Smith, Carl, Gallagher, Marcus and Hockings, Marc (2017). Use of freely available datasets and machine learning methods in predicting deforestation. Environmental Modelling and Software, 87, 17-28. doi: 10.1016/j.envsoft.2016.10.006

Use of freely available datasets and machine learning methods in predicting deforestation

Past funding

  • 2021 - 2022
    Solving Realistic Portfolio Optimisation Problems Using Interactive Multiobjective Evolutionary Algorithms (Defence Science and Technology Group grant administered by The University of Melbourne)
    University of Melbourne
    Open grant
  • 2019
    Machine Learning for Automated Network Anomaly Detection, Cyber Security and Analysis - Phase II
    Innovation Connections
    Open grant
  • 2018 - 2019
    Machine Learning for Automated Network Anomaly detection and Analysis
    Innovation Connections
    Open grant
  • 2016 - 2020
    Active and interactive analysis of prescription data for harm minimisation
    ARC Linkage Projects
    Open grant
  • 2013 - 2016
    The Development of Automated Advanced Data Analysis Techniques for the Detection of Aberrant Patterns of Prescribing Controlled Drugs
    ARC Linkage Projects
    Open grant
  • 2011 - 2013
    Data Mining Applications in the Regulation of Prescription Opioids
    Queensland Health
    Open grant
  • 2010 - 2012
    Understanding Patient Flow Bottlenecks and Patterns from Hospital Information Systems Data
    UQ Collaboration and Industry Engagement Fund
    Open grant
  • 2007 - 2009
    Metaheuristic Algorithms for Realistic Optimization Problems
    UQ Early Career Researcher
    Open grant
  • 2005 - 2006
    The Application of Machine Learning Techniques in Predicting Medical Outcomes
    UQ FirstLink Scheme
    Open grant
  • 2005 - 2006
    Smart Astronomy: Using Computational Science To Understand Distant Radio Galaxies
    ARC Special Research Initiatives - E-Research
    Open grant
  • 2005 - 2007
    A New Parallel Robot with breakthrough performance for Manufacturing of Aerospace Components - kinematic and dynamic synthesis, design optimisation and prototyping
    ARC Linkage Projects
    Open grant
  • 2001
    Population-based optimization algorithms and probabilistic modelling
    UQ New Staff Research Start-Up Fund
    Open grant

Availability

Associate Professor Marcus Gallagher is:
Available for supervision

Before you email them, read our advice on how to contact a supervisor.

Supervision history

Current supervision

  • Doctor Philosophy

    Adaptive Curriculums for Robotic Reinforcement Learning

    Principal Advisor

  • Doctor Philosophy

    Multi-objective optimisation and multi-agent learning for IoT devices.

    Principal Advisor

    Other advisors: Associate Professor Archie Chapman

  • Doctor Philosophy

    Hybrid local/global optimisation for the design of diverse structures

    Principal Advisor

  • Doctor Philosophy

    Improving neuroevolution using ideas from deep learning and optimization

    Principal Advisor

    Other advisors: Associate Professor Archie Chapman

  • Doctor Philosophy

    Generating data-driven continuous optimization problems for benchmarking

    Principal Advisor

    Other advisors: Professor Brian Lovell

  • Doctor Philosophy

    Towards Autonomous Network Security

    Associate Advisor

    Other advisors: Associate Professor Marius Portmann, Dr Siamak Layeghy

  • Doctor Philosophy

    Medical Image Segmentation with Limited Annotated Data

    Associate Advisor

    Other advisors: Professor Brian Lovell

  • Doctor Philosophy

    Characterizing Influence and Sensitivity in the Interpolating Regime

    Associate Advisor

    Other advisors: Professor Fred Roosta

  • Master Philosophy

    Forecasting and optimising decisions with machine learing

    Associate Advisor

Completed supervision

Enquiries

Contact Associate Professor Marcus Gallagher directly for media enquiries about:

  • Artificial Intelligence
  • Big Data
  • Computer programming
  • Data Science
  • Evolutionary algorithms
  • Evolutionary Computation
  • Heuristic optimisation
  • High-dimensional data - visualisation in computers
  • Intelligent systems
  • Machine learning
  • Neural networks
  • Optimisation Algorithms
  • Search space analysis - IT

Need help?

For help with finding experts, story ideas and media enquiries, contact our Media team:

communications@uq.edu.au