Computer Science

Dr Karl Mason

B.Sc., M.Sc., PhD

Biography

Dr. Karl Mason is a Lecturer Above the Bar (Assistant Professor) in the School of Computer Science at University of Galway. He is an SFI funded Principal Investigator. To date, he has secured over 1.6 million Euro in research funding from sources including: Science Foundation Ireland, Irish Research Council, Enterprise Ireland, and the Royal Irish Academy. He leads a team of 11 funded researchers within his research group at University of Galway.

Previously, he has held appointments as a Postdoctoral Researcher in the CIREGS lab at Cardiff University, UK. This work was funded by the EPSRC. He was also a Postdoctoral Fellow at the Georgia Institute of Technology, USA within the ACES Research Group, in collaboration with Sandia National Laboratories. Here, his work was funded by Sandia National Laboratories and the National Science Foundation. He completed his PhD research at University of Galway. His PhD dissertation was nominated for the European AI PhD Dissertation award.

His research interests include: neural networks, evolutionary computing, reinforcement learning, multi-agent systems and swarm intelligence. His research also includes applications of machine learning methods to problems including: renewable energy, smart homes, infrastructure planning, smart grid, robotics and cloud computing. He regularly reviews papers for top journals and serves on the program committee and senior program committee for multiple leading AI conferences, including: AAAI, AAMAS, ECAI and IJCAI. He was a guest editor in the 2023 special issue on Evolutionary Machine Learning for The Knowledge Engineering Review journal, published by Cambridge University Press. He has also organized multiple workshops at high profile AI conferences, e.g. ECAI and ECML.

Research URL: https://scholar.google.com/citations?user=kxcJG50AAAAJ&hl=en

Research Interests

Dr. Mason's research interests include:

Neural networks

Evolutionary computing

Reinforcement learning

Multi-agent systems

His research also includes applications of machine learning methods to problems including:

Renewable energy

Smart homes

Infrastructure planning

Smart grid

Robotics

Cloud computing

Peer Reviewed Journals

	Year	Publication
	(2020)	'A Deep Neural Network Approach for Behind-the-Meter Residential PV Size, Tilt and Azimuth Estimation' Mason, Karl and Reno, Matthew and Blakely, Logan and Vejdan, Sadegh and Grijalva, Santiago (2020) 'A Deep Neural Network Approach for Behind-the-Meter Residential PV Size, Tilt and Azimuth Estimation'. Solar Energy, 196 :260-269 [Details]
	(2019)	'A review of reinforcement learning for autonomous building energy management' Mason, Karl and Grijalva, Santiago (2019) 'A review of reinforcement learning for autonomous building energy management'. Computers & Electrical Engineering, 78 :300-312 [Details]
	(2018)	'A meta optimisation analysis of particle swarm optimisation velocity update equations for watershed management learning' Mason, Karl and Duggan, Jim and Howley, Enda (2018) 'A meta optimisation analysis of particle swarm optimisation velocity update equations for watershed management learning'. Applied Soft Computing, 62 :148-161 [Details]
	(2018)	'Predicting host CPU utilization in the cloud using evolutionary neural networks' Mason, Karl and Duggan, Martin and Barrett, Enda and Duggan, Jim and Howley, Enda (2018) 'Predicting host CPU utilization in the cloud using evolutionary neural networks'. Future Generation Computer Systems, 86 :162-173 [Details]
	(2018)	'Forecasting energy demand, wind generation and carbon dioxide emissions in Ireland using evolutionary neural networks' Mason, Karl and Duggan, Jim and Howley, Enda (2018) 'Forecasting energy demand, wind generation and carbon dioxide emissions in Ireland using evolutionary neural networks'. Energy, 155 :705-720 [Details]
	(2018)	'A multi-objective neural network trained with differential evolution for dynamic economic emission dispatch' Mason, Karl and Duggan, Jim and Howley, Enda (2018) 'A multi-objective neural network trained with differential evolution for dynamic economic emission dispatch'. International Journal Of Electrical Power & Energy Systems, 100 :201-221 [Details]
	(2018)	'Watershed Management using Neuroevolution' Mason, Karl and Duggan, Jim and Howley, Enda (2018) 'Watershed Management using Neuroevolution'. Modeling Earth Systems and Environment, [Details]
	(2017)	'Multi-objective dynamic economic emission dispatch using particle swarm optimisation variants' Mason, Karl and Duggan, Jim and Howley, Enda (2017) 'Multi-objective dynamic economic emission dispatch using particle swarm optimisation variants'. Neurocomputing, 270 :188-197 [Details]
	(2017)	'Policy invariance under reward transformations for multi-objective reinforcement learning' Mannion, Patrick and Devlin, Sam and Mason, Karl and Duggan, Jim and Howley, Enda (2017) 'Policy invariance under reward transformations for multi-objective reinforcement learning'. Neurocomputing, 263 :60-73 [Details]
	(2016)	'Exploring avoidance strategies and neighbourhood topologies in particle swarm optimisation' Mason, Karl and Howley, Enda (2016) 'Exploring avoidance strategies and neighbourhood topologies in particle swarm optimisation'. International Journal of Swarm Intelligence, 2 (2-4):188-207 [DOI] [Details]

Conference Publications

	Year	Publication
	(2019)	*IEEE International Conference on Big Data (Big Data)* Mason, Karl and Vejdan, Sadegh and Grijalva, Santiago (2019) An On The Fly Framework for Efficiently Generating Synthetic Big Data Sets IEEE International Conference on Big Data (Big Data) [Details]
	(2018)	*Adaptive and Learning Agents Workshop (at ICML-AAMAS 2018)* Mason, Karl and Duggan, Jim and Howley, Enda (2018) Maze Navigation using Neural Networks Evolved with Novelty Search and Differential Evolution Adaptive and Learning Agents Workshop (at ICML-AAMAS 2018) [Details]
	(2017)	*Adaptive and Learning Agents workshop (at AAMAS 2017)* Mannion, Patrick and Devlin, Sam and Mason, Karl and Duggan, Jim and Howley, Enda (2017) Potential-Based Reward Shaping Preserves Pareto Optimal Policies Adaptive and Learning Agents workshop (at AAMAS 2017) [Details]
	(2017)	*The 8th International Workshop on Cloud Applications and Security* Duggan, Martin and Mason, Karl and Duggan, Jim and Howley, Enda and Barrett, Enda (2017) Predicting Host CPU Utilization in Cloud Computing using Recurrent Neural Networks The 8th International Workshop on Cloud Applications and Security [Details]
	(2017)	*Proceedings of the Genetic and Evolutionary Computation Conference Companion* Mason, Karl and Duggan, Jim and Howley, Enda (2017) Evolving multi-objective neural networks using differential evolution for dynamic economic emission dispatch Proceedings of the Genetic and Evolutionary Computation Conference Companion , pp.1287-1294 [Details]
	(2017)	*Proceedings of the Genetic and Evolutionary Computation Conference Companion* Mason, Karl and Duggan, Jim and Howley, Enda (2017) Neural network topology and weight optimization through neuro differential evolution Proceedings of the Genetic and Evolutionary Computation Conference Companion , pp.213-214 [Details]
	(2016)	*ANTS 2016 International Conference in Swarm Intelligence* Mason, Karl and Kellehan, Caitriona and Duggan, Jim and Howley, Enda (2016) Particle Swarm Optimisation with Diversity Influenced Gradually Increasing Neighbourhoods ANTS 2016 International Conference in Swarm Intelligence [Details]
	(2016)	*ANTS 2016 International Conference in Swarm Intelligence* Mason, Karl and Duggan, Jim and Howley, Enda (2016) Avoidance Strategies for Particle Swarm Optimisation in Power Generation Scheduling ANTS 2016 International Conference in Swarm Intelligence [Details]
	(2016)	*Proceedings of the 2016 International Conference on Autonomous Agents \& Multiagent Systems* Mannion, Patrick and Mason, Karl and Devlin, Sam and Duggan, Jim and Howley, Enda (2016) Multi-objective dynamic dispatch optimisation using multi-agent reinforcement learning Proceedings of the 2016 International Conference on Autonomous Agents \& Multiagent Systems , pp.1345-1346 [Details]
	(2016)	*Proceedings of the Adaptive and Learning Agents workshop (at AAMAS 2016)* Mason, Karl and Mannion, Patrick and Duggan, Jim and Howley, Enda (2016) Applying multi-agent reinforcement learning to watershed management Proceedings of the Adaptive and Learning Agents workshop (at AAMAS 2016) [Details]
	(2016)	*International Conference on Soft Computing-MENDEL* Mason, Karl and Howley, Enda (2016) Avoidance strategies in particle swarm optimisation International Conference on Soft Computing-MENDEL , pp.3-15 [Details]
	(2016)	*Proceedings of the Adaptive and Learning Agents workshop (at AAMAS 2016)* Mannion, Patrick and Mason, Karl and Devlin, Sam and Duggan, Jim and Howley, Enda (2016) Dynamic economic emissions dispatch optimisation using multi-agent reinforcement learning Proceedings of the Adaptive and Learning Agents workshop (at AAMAS 2016) [Details]

Thesis

	Year	Publication
	(2018)	PhD Thesis, Advances in Evolutionary Neural Networks with Applications in Energy Systems and the Environment. Mason, Karl (2018) PhD Thesis, Advances in Evolutionary Neural Networks with Applications in Energy Systems and the Environment. Thesis [Details]
	(2015)	MSc Thesis, Avoidance techniques & neighbourhood topologies in particle swarm optimisation. Mason, Karl (2015) MSc Thesis, Avoidance techniques & neighbourhood topologies in particle swarm optimisation. Thesis [Details]