James Garland

MSc System Design (Microelectronic)

Assistant Lecturer

Carlow Campus

e: james.garland@itcarlow.ie      t: 059 9175442

ORCID ID: 0000-0002-8688-9407     ResearchGate  LinkedIn   Mendeley

PhD Candidate and researcher in Machine Learning. Lecturer and supervisor in undergrad and postgrad Electronics. Twenty-two years of industrial experience in software, FPGA & IC Design Engineering with Digital SoC/IP ASIC, FPGA and PCB design and test, training and customer support experience in various industries. Project manager, team and technical leader. Three years of External Examiner experience, eleven years of lecturing and research supervision experience.

  • ACADEMC AND RESEARCH EXPERIENCE
  • Publications and outputs
  • Research Supervision
  • Engagement and Collaboration

Academic and Research Experience

Research assistant on a PhD project designing low power embedded hardware for the SeNDT project in Trinity College Dublin, 2003-2004.

PhD Research Candidate, researching Micro-architectural Optimisations of Machine Learning Algorithms in FPGAs, ASICs and Embedded Systems for Increased Performance and Power, Area Conservation, 2016-2020. The thesis was submitted in 2020.

Current research interests include Micro-architectural optimisations in hardware and low-level software of artificial intelligence and machine learning algorithms. These optimisations aim to reduce power and gate count in FPGA and ASIC devices and increase performance in embedded low power IoT Edge devices.

Publications and Outputs

Peer Reviewed Journal Articles

Garland, J. and Gregg D. (2018) ‘Low Complexity Multiply Accumulate Units for Convolutional Neural Networks with Weight-Sharing’, in ACM Transactions on Architecture and Code Optimisation (TACO), vol. 15, no. 3, August 2018, Article 31, pp. 1-24, DOI: 10.1145/3233300

Garland, J. and Gregg D. (2017) ‘Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks’, in IEEE Computer Architecture Letters, vol. 16, no. 2, pp. 132-135, July-Dec. 1 2017, DOI: 10.1109/LCA.2017.2656880

Book Chapters

Anderson, A; Garland, J; Wen, Y; Barabasz, B; Persand, K; Vasudevan, A; Gregg, D. (2019) Chapter 6, ‘Hardware and software performance in deep learning’ in ‘Many-Core Computing: Hardware and Software’, pp: 141-161, ISBN: 978-1-78561-582-5.

Garland, J. and Gregg D. (2017) ‘Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks’, in ‘ACACES 2017 Poster Abstracts’, pp. 53-56, HiPEAC, the European Network of Excellence on High Performance and Embedded Architecture and Compilation.

Conference Proceedings and Papers

Garland, J. and Gregg D. (2019) ‘Low Complexity Multiply-Accumulate Units for Convolutional Neural Networks with Weight-Sharing’, talk at HiPEAC January 2019, Valencia, Spain.

Garland, J. and Gregg D. (2017) ‘Low Complexity Multiply Accumulate Unit for Weight-Sharing Convolutional Neural Networks’, Poster presentation, HiPEAC ACACES 2017, Fiuggi, Italy.

Research Supervision

Current Research Students

2019-Present, Institute of Technology, Carlow-

  • Bovenizer, Christopher (2020-2022), IRC Employment-Based Program M.Sc., “Live, On-site Automation of Harvesting Equipment using Artificial Intelligence, Vision and
  • Sensor Systems”, Institute of Technology, Carlow and Tanco Autowrap Limited.
  • Furlong, Ryan (2019-2021), President’s EngCore Research Fellowship M.Sc., “Development platform for Artificial Intelligence at the network edge”.
  • Connolly, Luke (2019-2021), President’s EngCore Research Fellowship M.Sc., “UAV obstacle avoidance”, Institute of Technology, Carlow.
Past research students

2019, Institute of Technology Carlow-

  • Brennan, Colm (2019), M.Sc. in Communications Technology Management, “How can Machine Learning be Applied to Maritime Data Information to Aid Targeted Patrolling by the Irish Naval Service?”

2006-2008, Trinity College Dublin-

Areas of Interest as a Supervisor include
  • Machine Learning
  • ASIC and FPGA design
  • Embedded Computing and Sensor systems
  • Electronics

Engagement and Collaboration

Research Funding