Skip to main content

Machine Learning

Machine Learning (ML) is seen as a subset of Artificial Intelligent (AI) where intelligent algorithms autonomously learn concepts and latent patterns from data to perform different tasks. ML models utilize a variety of techniques to intelligently handle large and complex amounts of information to make human-like decisions. ML models explore the fundamental principles in many disciplines, including statistics, graph theory, mathematical optimization, knowledge representation, planning and control, data analytics, causal inference, computer systems, computer vision, and natural language processing in order to solve complex problems. Machine learning algorithms can impact many applications relying on all sorts of data, such as medical health data, scientific data, financial data, security data, weather data, energy data, and data from any active or passive sensing instruments. WVU faculties have developed novel ML algorithms for specific tasks in health sciences, defense, homeland security, cybersecurity and energy.

Affiliated Faculty

Recent Publications

  1. F. Taherkhani, H Kazemi, A. Dabouei, J. Dawson, N. M. Nasrabadi, “A Weakly Supervised Fine Label Classifier Enhanced by Coarse Supervision,” IEEE International Conference on Computer Vision (ICCV'19), Oct. 23-Nov.2, 2019, Seoul, Korea.
  2. F. Taherkhani, H. Kazemi, N. M. Nasrabadi, “Matrix Completion for Graph-Based Deep Semi-Supervised Learning”, 33rd AAAI Conference on Artificial Intelligence (AAAI’19), Jan. 27-Feb. 1, 2019, Honolulu, Hawaii.
  3. H. Kazemi, M. Iranmanesh, F. Taherkhani, S. Soleymani, N. M. Nasrabadi, “Unsupervised Image-to-Image Translation Using Domain-Specific Variational Information Bound,” Thirty-second Conference on Neural Information Processing Systems (NIPS’18), 4-6 Dec. 2018, Montreal, Canada.
  4. S Motiian, M Piccirilli, DA Adjeroh, G Doretto, “Unified deep supervised domain adaptation and generalization,” IEEE International Conference on Computer Vision (ICCV’17), pp. 5716—5726, 2017.
  5. S Motiian, M Piccirilli, DA Adjeroh, G Doretto, “Information Bottleneck Learning Using Privileged Information for Visual Recognition,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR’16), pp. 1496-1505, 2016.
  6. F Siyahjani, R Almohsen, S Sabri, G Doretto, “A Supervised Low-Rank Method for Learning Invariant Subspaces,” IEEE International Conference on Computer Vision (ICCV’15), 4220-4228, 2015.