Back
  1. Home
  2. Profile of Decebal Constantin MOCANU (Unilu)
Profil

MOCANU Decebal Constantin

University of Luxembourg > Faculty of Science, Technology and Medicine (FSTM) > Department of Computer Science (DCS)

ORCID
0000-0002-5636-7683
Main Referenced Co-authors
Pechenizkiy, Mykola (5)
Grooten, Bram (3)
Mocanu, Elena (3)
Liu, Shiwei (2)
Sokar, Ghada (2)
Main Referenced Keywords
Sparse Neural Networks (6); Computer Science - Computer Vision and Pattern Recognition (5); Computer Science - Learning (5); Sparse Training (4); Computer Science - Artificial Intelligence (3);
Main Referenced Disciplines
Computer science (8)

Publications (total 8)

The most downloaded
8 downloads
Grooten, B., Tomilin, T., Vasan, G., Taylor, M. E., Mahmood, R. A., Fang, M., Pechenizkiy, M., & MOCANU, D. C. (In press). MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning. In AAMAS '24: Proceedings of the 2024 International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC. https://hdl.handle.net/10993/59778

The most cited

326 citations (Scopus®)

MOCANU, D. C., Mocanu, E., Stone, P., Nguyen, P. H., Gibescu, M., & Liotta, A. (19 June 2018). Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature Communications, 9 (1), 2383. doi:10.1038/s41467-018-04316-3 https://hdl.handle.net/10993/57170

Grooten, B., Tomilin, T., Vasan, G., Taylor, M. E., Mahmood, R. A., Fang, M., Pechenizkiy, M., & MOCANU, D. C. (In press). MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning. In AAMAS '24: Proceedings of the 2024 International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC.
Peer reviewed

Wu, B., Xiao, Q., Liu, S., Yin, L., Pechenizkiy, M., MOCANU, D. C., Van Keulen, M., & Mocanu, E. (2023). E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation. ORBilu-University of Luxembourg. https://orbilu.uni.lu/handle/10993/59774.

Yildirim, M. O., Gok Yildirim, E. C., Sokar, G., MOCANU, D. C., & Vanschoren, J. (20 November 2023). Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates [Paper presentation]. CPAL 2024: Conference on Parsimony and Learning.
Peer reviewed

Grooten, B., Sokar, G., Dohare, S., Mocanu, E., Taylor, M. E., Pechenizkiy, M., & MOCANU, D. C. (2023). Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning. In AAMAS '23: Proceedings of the 2023 International Conference on Autonomous Agents and Multiagent Systems. International Foundation for Autonomous Agents and Multiagent Systems, Richland, SC.
Peer reviewed

Atashgahi, Z., Pechenizkiy, M., Veldhuis, R., & MOCANU, D. C. (2023). Adaptive Sparsity Level during Training for Efficient Time Series Forecasting with Transformers. ORBilu-University of Luxembourg. https://orbilu.uni.lu/handle/10993/59769.

Liu, S., Chen, T., Chen, X., Chen, X., Xiao, Q., Wu, B., Kärkkäinen, T., Pechenizkiy, M., MOCANU, D. C., & Wang, Z. (01 February 2023). More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity [Paper presentation]. ICLR 2023: The Eleventh International Conference on Learning Representations.
Peer reviewed

Nowak, A. I., Grooten, B., MOCANU, D. C., & Tabor, J. (2023). Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training [Paper presentation]. NeurIPS 2023: Thirty-seventh Annual Conference on Neural Information Processing Systems.
Peer reviewed

MOCANU, D. C., Mocanu, E., Stone, P., Nguyen, P. H., Gibescu, M., & Liotta, A. (19 June 2018). Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nature Communications, 9 (1), 2383. doi:10.1038/s41467-018-04316-3
Peer Reviewed verified by ORBi

Contact ORBilu