Computer Engineering, University of Kurdistan, Iran
The AML team is part of the Representation Learning Lab, affiliated with the Department of Computer Engineering at the University of Kurdistan, Iran.
Algebraic Machine Learning is a machine learning approach using the mathematics of Model Theory to naturally embed what we know about data and formal knowledge into a discrete algebraic structure.
Our algorithms build upon linear algebraic, geometric, probabilistic, and deep learning operations. Additionally, we attempt to develop theoretical foundations of the effect and principles underlying our algorithmic approaches.
Our current algebraic machine learning projects are mainly focused on the following directions:
To learn data representations to facilitate data understanding based on visual observation.
To understand and mitigate the trade-off between model robustness and accuracy by both theoretical and empirical studies.
To seek effective solutions addressing the deficiency of large-scale, noisy data with high redundancy, missing and small data situations, and inadequate labeling cases.
To leverage multimodal data collected from different information resources and characterized by different feature views.
Fardin is an associate professor of Computer engineering at the University of Kurdistan. His research focuses on machine learning, computer vision, and data mining. He did his PhD in Computer Vision at the University of Wollongong in 2005. He held a master's degree in Telecommunications and Signal Processing from the University of Tarbiat Modarres in 1992.
Amjad is a graduate research assistant at the University of Kurdistan working on deep learning. He received his Master's in Artificial Intelligence from the Department of Computer Engineering at the University of Kurdistan in 2018. His work mainly focused on matrix factorization, low-rank approximation, and regression models.
Distributionally Robust Learning
Wafa is a faculty member of the Computer Engineering Department, at the Kermanshah University of Technology.
Deep Multi-label Learning
Reza has completed his master's degree in AML team.
Text Clustering/Topic Modeling(Co-Supervisor: Dr. Daneshfar)
Multi-Objective Recommendation Systems
Anomaly Detection
Hyperspectral Unmixing
Multi-View Representation
Deep Self-Representation Learning
Self-supervised Semi-supervised Learning
Unsupervised Feature Selection(Co-Supervisor: Dr. Pir Mohammadiani)
Link Prediction by Adversarial Training(Co-Supervisor: Dr. Abdollahpouri)
Directed Graph Clustering
Robust Data Representation
Multi-label feature selection
Attributed Graph Clustering(Co-Supervisor: Dr. Pir Mohammadiani)