Skip to main content

Deep Learning

Deep Learning (DL) is a machine learning technique that teaches computers to do high level tasks that are often natural to humans. DL models are based on artificial neural networks which are inspired by the human brain biological neural circuits. DL models analyze data and enable machines to exhibit human-like cognition. They can achieve state-of-the-art accuracy, sometimes exceeding human-level performance. DL models learn by examples, they are trained by using a large set of labeled/unlabeled data, utilizing supervised, unsupervised or semi-supervised training frameworks. WVU faculties have been working on deep learning as one of the key technologies to solve engineering problems in automated driving, biometrics, health sciences, natural language understanding, satellite image analysis, aerospace and defense applications, medical research, consumer electronics, geography and geology, energy exploration, cybersecurity, time-series prediction, and industrial manufacturing.

Affiliated Faculty

Recent Publications

  1. Ali Dabouei, Sobhan Soleymani, Fariborz Taherkhani, Jeremy Dawson, Nasser M. Nasrabadi, “Exploiting Joint Robustness to Adversarial Perturbations,” Computer Vision and Pattern Recognition (CVPR 2020), June 14-19, 2020, Seattle, Washington.
  2. Xiaoxia Sun, Nasser M. Nasrabadi and Trac D. Tran, "Supervised Deep Sparse Coding Networks for Image Classification," IEEE Trans. on Image Processing, vol. 29, no. 7, pp. 405-418, July 17, 2019.
  3. Zhangming Ding, Nasser M. Nasrabadi, Yun Fu, “Semi-supervised Task-driven Deep Transfer Learning via Coupled Neural Networks,” IEEE Transaction on Image Processing, vol. 27, issue 11, pp. 5214-5224, June 2018.
  4. Stanislav Pidhorskyi Ranya Almohsen Donald A. Adjeroh Gianfranco Doretto, “Generative Probabilistic Novelty Detection with Adversarial Autoencoders,” Advances in neural information processing systems, 31, 6822-6833, 2018.
  5. Stanislav Pidhorskyi, Donald A Adjeroh, Gianfranco Doretto, “Adversarial Latent Autoencoders,” in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 14104-14113, 2020.
  6. Syed Ashiqur Rahman, Peter Giacobbi, Lee Pyles, Charles Mullett, Gianfranco Doretto, Donald A Adjeroh, “Deep Learning for Biological Age Estimation,” Briefings in Bioinformatics, 2020.