Decebal Constantin Mocanu
Universiteit Twente
H-index: 28
Europe-Netherlands
Top articles of Decebal Constantin Mocanu
Title | Journal | Author(s) | Publication Date |
---|---|---|---|
MaDi: Learning to Mask Distractions for Generalization in Visual Deep Reinforcement Learning | arXiv preprint arXiv:2312.15339 | Bram Grooten Tristan Tomilin Gautham Vasan Matthew E Taylor A Rupam Mahmood | 2023/12/23 |
Supervised Feature Selection via Ensemble Gradient Information from Sparse Neural Networks | Kaiting Liu Zahra Atashgahi Ghada Sokar Mykola Pechenizkiy Decebal Constantin Mocanu | 2024/4/18 | |
FOCIL: Finetune-and-Freeze for Online Class Incremental Learning by Training Randomly Pruned Sparse Experts | arXiv preprint arXiv:2403.14684 | Murat Onur Yildirim Elif Ceren Gok Yildirim Decebal Constantin Mocanu Joaquin Vanschoren | 2024/3/13 |
Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning | arXiv preprint arXiv:2302.06548 | Bram Grooten Ghada Sokar Shibhansh Dohare Elena Mocanu Matthew E Taylor | 2023/2/13 |
Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training | Aleksandra Irena Nowak Bram Grooten Decebal Constantin Mocanu Jacek Tabor | 2023 | |
Hu-bot: promoting the cooperation between humans and mobile robots | Neural Computing and Applications | Karine Miras Decebal Mocanu AE Eiben | 2023/8 |
Adaptive sparsity level during training for efficient time series forecasting with transformers | arXiv preprint arXiv:2305.18382 | Zahra Atashgahi Mykola Pechenizkiy Raymond Veldhuis Decebal Constantin Mocanu | 2023/5/28 |
More convnets in the 2020s: Scaling up kernels beyond 51x51 using sparsity | ICLR 2023, The Eleventh International Conference on Learning Representations, arXiv preprint arXiv:2207.03620 | Shiwei Liu Tianlong Chen Xiaohan Chen Xuxi Chen Qiao Xiao | 2023/5 |
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation | arXiv preprint arXiv:2312.04727 | Boqian Wu Qiao Xiao Shiwei Liu Lu Yin Mykola Pechenizkiy | 2023/12/7 |
Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks | TMLR, Transactions on Machine Learning Research | Zahra Atashgahi Xuhao Zhang Neil Kichler Shiwei Liu Lu Yin | 2023/2 |
Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates | CPAL 2024, Conference on Parsimony and Learning, arXiv:2308.14831 | Murat Onur Yildirim Elif Ceren Gok Yildirim Ghada Sokar Decebal Constantin Mocanu Joaquin Vanschoren | 2023/11/20 |
A Brain-inspired Algorithm for Training Highly Sparse Neural Networks | Machine Learning Journal (ECML-PKDD 2022 journal track) | Zahra Atashgahi Joost Pieterse Shiwei Liu Decebal Constantin Mocanu Raymond Veldhuis | 2022 |
Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training | Lu Yin Vlado Menkovski Meng Fang Tianjin Huang Yulong Pei | 2022/2/28 | |
Dynamic Sparse Training for Deep Reinforcement Learning | IJCAI-ECAI 2022 (best paper award at ALA 2022), 31st International Joint Conference on Artificial Intelligence, arXiv preprint arXiv:2106.04217 | Ghada Sokar Elena Mocanu Decebal Constantin Mocanu Mykola Pechenizkiy Peter Stone | 2022/7 |
Dynamic Sparse Network for Time Series Classification: Learning What to “See” | Qiao Xiao Boqian Wu Yu Zhang Shiwei Liu Mykola Pechenizkiy | 2022/11 | |
Situation-aware drivable space estimation for automated driving | IEEE Transactions on Intelligent Transportation Systems | Manuel Muñoz Sánchez Denis Pogosov Emilia Silvas Decebal Constantin Mocanu Jos Elfring | 2022/6/22 |
Where to Pay Attention in Sparse Training for Feature Selection? | NeurIPS2022, 36th Annual Conference on Neural Information Processing Systems | Ghada Sokar Zahra Atashgahi Mykola Pechenizkiy Decebal Constantin Mocanu | 2022/11/26 |
Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks | ECMLPKDD 2022, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, arXiv preprint arXiv:2110.05329 | Ghada Sokar Decebal Constantin Mocanu Mykola Pechenizkiy | 2022/6/14 |
Towards Implementing Truly Sparse Connections in Deep RL Agents | Bram J Grooten Ghada Sokar Elena Mocanu Shibhansh Dohare Matthew E Taylor | 2022/7/13 | |
The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training | ICLR 2022, The Tenth International Conference on Learning Representations, arXiv preprint arXiv:2202.02643 | Shiwei Liu Tianlong Chen Xiaohan Chen Li Shen Decebal Constantin Mocanu | 2022/4 |