| SpaceNet: Make Free Space For Continual Learning G Sokar, DC Mocanu, M Pechenizkiy Elsevier Neurocomputing Journal, 2020 | 76 | 2020 |
| Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity S Liu, T Chen, Z Atashgahi, X Chen, G Sokar, E Mocanu, M Pechenizkiy, ... ICLR 2022.The Tenth International Conference on Learning Representations, 2021 | 51 | 2021 |
| The Dormant Neuron Phenomenon in Deep Reinforcement Learning G Sokar, R Agarwal, PS Castro, U Evci ICML2023, International Conference on Machine Learning, Oral, 2023 | 50 | 2023 |
| Dynamic Sparse Training for Deep Reinforcement Learning G Sokar, E Mocanu, DC Mocanu, M Pechenizkiy, P Stone IJCAI-ECAI 2022. The 31st International Joint Conference on Artificial
, 2021 | 39 | 2021 |
| Topological Insights in Sparse Neural Networks S Liu, T Van der Lee, A Yaman, Z Atashgahi, D Ferraro, G Sokar, ... ECML PKDD 2020, 2020 | 35* | 2020 |
| Quick and robust feature selection: the strength of energy-efficient sparse training for autoencoders Z Atashgahi, G Sokar, T van der Lee, E Mocanu, DC Mocanu, R Veldhuis, ... Machine Learning, 1-38, 2022 | 21 | 2022 |
| A generic OCR using deep siamese convolution neural networks G Sokar, EE Hemayed, M Rehan 2018 IEEE 9th Annual Information Technology, Electronics and Mobile
, 2018 | 20 | 2018 |
| Where to Pay Attention in Sparse Training for Feature Selection? G Sokar, Z Atashgahi, M Pechenizkiy, DC Mocanu NeurIPS2022, 36th Annual Conference on Neural Information Processing Systems, 2022 | 16 | 2022 |
| Self-Attention Meta-Learner for Continual Learning G Sokar, DC Mocanu, M Pechenizkiy AAMAS 2021. 20th International Conference on Autonomous Agents and
, 2021 | 16 | 2021 |
| Quick and robust feature selection: the strength of energy-efficient sparse training for autoencoders Z Atashgahi, G Sokar, T van der Lee, E Mocanu, DC Mocanu, R Veldhuis, ... Machine Learning Journal, 2020 | 15 | 2020 |
| Learning Invariant Representation for Continual Learning G Sokar, DC Mocanu, M Pechenizkiy AAAI Workshop on Meta-Learning for Computer Vision (AAAI-2021), 2020 | 14 | 2020 |
| Avoiding Forgetting and Allowing Forward Transfer in Continual Learning via Sparse Networks G Sokar, DC Mocanu, M Pechenizkiy ECMLPKDD2022, 2021 | 12* | 2021 |
| Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning B Grooten, G Sokar, S Dohare, E Mocanu, ME Taylor, M Pechenizkiy, ... AAMAS 2023. 22nd International Conference on Autonomous Agents and
, 2023 | 11 | 2023 |
| Mixtures of experts unlock parameter scaling for deep rl J Obando-Ceron, G Sokar, T Willi, C Lyle, J Farebrother, J Foerster, ... arXiv preprint arXiv:2402.08609, 2024 | 7 | 2024 |
| Continual learning with dynamic sparse training: Exploring algorithms for effective model updates MO Yildirim, EC Gok, G Sokar, DC Mocanu, J Vanschoren Conference on Parsimony and Learning, 94-107, 2024 | 3 | 2024 |
| FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity S Liu, T Chen, Z Atashgahi, X Chen, G Sokar, E Mocanu, M Pechenizkiy, ... ICLR 2022.The Tenth International Conference on Learning Representations, 2021 | 3 | 2021 |
| Dynamic sparse training for deep reinforcement learning (poster) GAZN Sokar, E Mocanu, DC Mocanu, M Pechenizkiy, P Stone Sparsity in Neural Networks: Advancing Understanding and Practice 2021, 2021 | 2 | 2021 |
| Continual Lifelong Learning for Intelligent Agents G Sokar IJCAI 2021. International Joint Conferences on Artifical Intelligence (IJCAI), 2021 | 1 | 2021 |
| Mixtures of Experts Unlock Parameter Scaling for Deep RL JSO Ceron, G Sokar, T Willi, C Lyle, J Farebrother, JN Foerster, ... Forty-first International Conference on Machine Learning, 0 | 1 | |
| Training neural networks by resetting dormant neurons U Evci, PSC Rivadeneira, GAERZN Sokar, R Agarwal US Patent App. 18/424,633, 2024 | | 2024 |
Decebal Constantin MocanuAssociate Professor in Machine Learning, University of Luxembourg, TU EindhovenPatvirtintas el. paštas uni.lu
