Dr Omid Chatrabgoun is an Assistant Professor in Data Science and AI. He received PhD in Mathematical Statistics from Shahid Chamran University (Iran) in 2015 for a thesis entitled "Estimating Copula Density Function through Multiwavelets".  After graduation, he started working at Malayer University, Iran. He continued learning about data science and mostly focused on copula-based supervised and un-supervised learning.  Also, he started working on machine learning techniques. During his academic career, he has taught some courses relating to his expertise at undergraduate and postgraduate levels, including Statistical learning, Data science, and Machine learning. His primary research is in Data Science using (Deep) Gaussian process and kernel-based Support Vector machines (SVMs), Big data and Machine learning (Especially (Deep) Gaussian process, Neural networks and Stochastic differential equation). He is currently developing a novel approach for Machine learning of linear operational equations to model uncertainty quantification for highly complex systems using Gaussian processes. He has applied these methods to a wide range of applications in various multidisciplinary projects including construction of Gene Regulatory Networks (GRNs).

Dr Omid Chatrabgoun is co-author of many research outputs, published as peer-reviewed papers, book chapters and conference presentations. He has experience of gaining research grants and has been involved in consultancy and knowledge exchange projects with a range of research and industrial centres including Iran National Science Foundation (INSF) and Research Institute for Grapes and Raisin (RIGR).

Constructing gene and protein network using machine learning techniques (Especially Kernel-based approach and Gaussian process);

• Copula technique in supervised and unsupervised learning;

• Machine learning and Bayesian inference – Approximate Bayesian computation – Non-parametric Bayesian inference (mostly with Gaussian process models) – Simulating/approximating the complex systems using Gaussian processes;

• Modelling high-dimensional data using Graphical models (including Bayesian networks, Dynamic Bayesian networks, and Pair-copula Bayesian models);

• Dimensionality reduction using Gaussian process Latent Variable model and Kernel-based probabilistic nonlinear PCA;

• Inverse problem for linear operational equations using Gaussian process;

• Supervised/Un-supervised learning using Gaussian process;

• Machine learning techniques ((Deep) Neural networks and (Deep) Gaussian proccess) for solving stochastic differential equations;