Dr Bo Liu
- Senior Lecturer (Systems Power & Energy)
Research interests
Biography
Bo Liu received the B.Eng. degree from Tsinghua University, China, in 2008 and the Ph.D. degree from University of Leuven (KU Leuven), Belgium, in 2012. From October 2012 he held the distinguished position of Humboldt Research Fellow, working with the Technical University of Dortmund, Germany. From April 2013, he was a Lecturer (Assistant Professor) at Wrexham Glyndwr University, UK, where he was promoted to Reader (Associate Professor) in 2016. He joined in University of Glasgow as a Senior Lecturer (Associate Professor) in 2020. He is a Senior Member of the IEEE.
Dr. Liu’s research focuses on AI-driven electronic design. His main contributions and research highlights include:
- Being the first to introduce bespoke heuristic optimization techniques into analog IC sizing (2008-2009).
- Being the first to introduce online machine learning-assisted optimization into high-frequency device synthesis (2011) and to enable it to address complex mm-wave ICs (2014).
- Being the first to address the bottleneck of computationally expensive EM simulations together with poor initial design in antenna and filter synthesis, which is an essential step for transforming AI-driven antenna/filter design from laboratory to industry. (2013-2014, 2017) The first to enable AI-driven design techniques to handle complex antennas with more than 50 design variables and many specifications (2020).
- His proposed AI-driven analog IC, microwave antenna, filter, and MEMS design methods are being used as essential tools by many international leading design teams (in both academia and industry). Some of the proposed AI-driven design methods are the only viable solution for complex antennas/filters and high-performance analog ICs.
- Some of his proposed AI-driven electronic design algorithms rank first in industry testing and comparisons, which have been embedded into MATLAB and are currently under discussion to be embedded into more renowned CAD tools.
Research interests
Just as steam engines allowed mass production of labour-intensive products, AI techniques have the potential to realize mass production of knowledge and intelligence-intensive products. However, there is currently a gap between off-the-shelf AI techniques and real-world electronic design. Filling this gap, in order to transform AI techniques for electronic design from laboratory to industry, is the aim of my research. My research focuses on machine learning and data-driven optimization-based methodology for electronic circuit and system design, unblocking bottlenecks in design complexity and time-to-market. In particular, the following research directions are critical:
- Novel data-driven optimization and machine learning algorithms for electronic (analog ICs and systems, microwave devices, and micro-electromechanical systems) design
- Mixed intelligence electronic design methodologies hybridizing AI techniques, domain knowledge, and the designer's intelligence
- AI-driven design in real-world electronic engineering
- Computer-aided design tools implementing AI-driven electronic design and data analysis methods
More details of my research can be found on my Google Scholar page: https://scholar.google.com/citations?user=G-K3GC0AAAAJ&hl=en
Considering all this, I am now welcoming highly motivated PhD students, postdocs, and visiting researchers who have the ambition to change ways of working for future electronic engineers: from experience-driven design to AI-driven design!
Students/Researchers with the following backgrounds are extremely welcome:
- AI background: You will be the core of the team. Instead of using mathematical benchmark problems, you will use real-world electronic design optimization/synthesis/modeling problems to identify the challenges of existing AI techniques and generate novel and high-performance AI algorithms ready for EE industry use.
- EE background: For many design problems, the power of AI techniques alone is insufficient and design knowledge must be an equal partner to form a mixed intelligence approach. You will be the core of such novel techniques. You will also be armed with AI knowledge and realize them in real-world analog IC/biomedical system/antenna/filter/diplexer/MEMS/… design, being the first generation of electronic design engineers to apply such AI techniques.
- Software engineering background: The successful AI-driven design methodologies will be transferred to intelligent CAD tools. You will be the person to embed the new algorithms into renowned CAD tools, and millions of engineers will use your code. You will also develop our own CAD tools, which will be used by leading international design teams. Proposing novel human-computer interaction methods with electronic engineers will also be your playground.
So, let us launch the AI-driven electronic design research area together!
Interested students/researchers, please send me your CV along with a brief description of your background and research interest(s)/direction(s). For potential funding opportunities, please visit the supervision section.
Always welcome visiting scholars focusing on SOFTWARE ENGINEERING
CURRENT FULLY FUNDED PHD OPPORTUNITIES
PhD Studentship in AI Techniques for Automated Design of Microwave Antennas (Funded by The MathWorks Inc., application deadline: April 30, 2020)
PhD Studentship in Engineering Optimization (Funded by EIT-CDT and industrial partners, application deadline: June 30, 2020)
Grants
- Principal Investigator, "AI-driven antenna design exploration software tool development", EPSRC IAA, £36,000, 2021.
- Principal Investigator, “Next-generation AI-driven CAD technology for electromagnetic devices”, MathWorks (65%) + University matching (35%), £168,000, 2020-2023.
- Senior Consultant (working as principal investigator), “Integrating human and machine intelligence for next-generation interactive analog IC design”, USA National Science Foundation, $799,998 (33%), 2017-2021.
- Supervisor, mobility funding for the Artificial Intelligence-Driven Engineering Design Automation, European Community Action Scheme for the Mobility of University Students, £ 60,204. 2017-2019.
- Principal Investigator, “Efficient black-box optimization of computationally expensive problems, with applications to electromagnetic design automation”, Alexander von Humboldt Foundation (postdoctoral researcher), €76,800, 2012-2013.
- Principal Investigator, “Computational intelligence techniques for automated design of analog and high-frequency circuits”, Belgium Government Scholarship (PhD researcher), €66,960, 2008-2012.
- Principal Supporting Scientist, “Intelligent algorithm-based parameter extraction for high-frequency electronic devices”, Accelicon Technologies Inc, $10,000, 2008-2009.
- Welsh government CRISP funding: £5,000, 2015.
- Innovate UK innovative voucher: £5,000, 2015.
Supervision
I have successfully supervised three PhD students, obtaining high-quality research outcomes. I am leading the AI-driven design lab (7 PhD students and research assistants) now.
I am welcoming highly motivated PhD students, postdocs, and visiting researchers who have the ambition to change ways of working for future electronic engineers: from experience-driven design to AI-driven design!
Students/Researchers with the following backgrounds are extremely welcome:
- AI background: You will be the core of the team. Instead of using mathematical benchmark problems, you will use real-world electronic design optimization/synthesis/modeling problems to identify the challenges of existing AI techniques and generate novel and high-performance AI algorithms ready for EE industry use.
- EE background: For many design problems, the power of AI techniques alone is insufficient and design knowledge must be an equal partner to form a mixed intelligence approach. You will be the core of such novel techniques. You will also be armed with AI knowledge and realize them in real-world analog IC/biomedical system/antenna/filter/diplexer/MEMS/… design, being the first generation of electronic design engineers to apply such AI techniques.
- Software engineering background: The successful AI-driven design methodologies will be transferred to intelligent CAD tools. You will be the person to embed the new algorithms into renowned CAD tools, and millions of engineers will use your code. You will also develop our own CAD tools, which will be used by leading international design teams. Proposing novel human-computer interaction methods with electronic engineers will also be your playground.
AI-driven electronic design is at its early stage, but it will be the future. So, let us launch the AI-driven electronic design research area together!
Interested students/researchers, please send me your CV along with a brief description of your background and research interest(s)/direction(s). For potential funding opportunities, please visit the supervision section.
Always welcome visiting scholars focusing on SOFTWARE ENGINEERING
CURRENT FULLY FUNDED PHD OPPORTUNITIES
PhD Studentship in AI Techniques for Automated Design of Microwave Antennas (Funded by The MathWorks Inc., application deadline: April 30, 2020)
PhD Studentship in Engineering Optimization (Funded by EIT-CDT and industrial partners, application deadline: June 30, 2020)
Funding opportunities:
PhD students:
Scholarship from School of Engineering, University of Glasgow: https://www.gla.ac.uk/colleges/scienceengineering/graduateschool/scholarships/
If you are a Chinese student, you may apply for CSC scholarship:
There is also a special opportunity for University of Glasgow:
http://www.csc.edu.cn/require/projects2017/200042.pdf
Fellowships for Postdocs/Visiting Researchers:
EPSRC Fellowships
The Leverhulme Trust Early Career Fellowships
Royal Academy of Engineering Fellowships
British Academy Postdoctoral Fellowships
Newton International Fellowships
Marie Skłodowska-Curie actions - Research Fellowship
CSC postgraduate scholarship
Teaching
My teaching interests locate in computer science education to engineering students, mainly including programming languages (e.g., C, MATLAB) and AI techniques. Different from traditional computer science education, my teaching aims at arming engineering students with problem-solving skills using computer programs and state-of-the-art AI techniques.
Currently, I am teaching at Glasgow College of University of Electronic Science & Technology of China (UESTC).
Additional information
Bo's non-work activities
https://www.facebook.com/profile.php?id=100014282528179