About Me
News
- 22 September, 2023 I gave a keynote talk about "Sparse training of neural networks" at the E-pi: Re-thinking Uncertainty and AI Workshop in TU Delft (link)
- 6 June, 2023 I am doing a short research visit and hold a seminar about "Sparse Training in Deep Reinforcement Learning" at CaSToRC, the National HPC Competence Center - The Cyprus Institute (link)
- 24 April, 2023 Our tutorial "Sparse Training for Supervised, Unsupervised, Continual, and Deep Reinforcement Learning with Deep Neural Networks" has been accepted at IJCAI 2023.
- 11 April, 2023 I gave an invited talk on "Sparsity in neural networks" at the Big Data & AI workshop during the Smart Diaspora 2023 conference in Timisoara, Romania.
- 30 January, 2023 I gave an invited talk on "Scalable and Efficient Agents using Sparse Neural Networks" at the AI for E&S Think Tank, TU Delft (link)
- 4 January, 2023 Our paper "Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning" has been accepted at AAMAS 2023 (link)
- 4 January, 2023 The third edition of the workshop "Sparsity in Neural Networks: On practical limitations and tradeoffs between sustainability and efficiency" - SNN 2023 will be colocated with ICLR 2023 (link)
- 27 October, 2022 I gave an invited talk at the CoMBE Seminar Series, University of Duisburg-Essen
- 14 September, 2022 One paper on sparse training and time series classification accepted at NeurIPS 2022 (link)
- 15 July, 2022 I gave an invited talk during the AI Seminar at the University of Alberta/Alberta Machine Intelligence Institute titled "Sparse training in supervised, unsupervised, and deep reinforcement learning" (link)
- 13 July, 2022 I was recognised as an Outstanding Reviewer at ICML 2022
- 13 July, 2022 We are organising the second edition of the "Sparsity in Neural Networks: Advancing Understanding and Practice" Workshop - SNN 2022 (link)
- 10 June, 2022 I gave an invited talk at Calgary AI, University of Calgary
- 21 May, 2022 I am doing a research visit to the group of Dr. Matthew Taylor at the University of Alberta
- 10 May, 2022 Our paper "Dynamic Sparse Training for Deep Reinforcement Learning" received best paper award at ALA 2022, collocated with AAMAS 2022 (link)
- 25 April, 2022 We had the pleasure of hosting Utku Evci, Research Engineer at Google Brain Montreal, to give a very engaging in-person talk.
- 20 April, 2022 One paper on sparse training and deep reinforcement learning accepted at IJCAI-ECAI 2022 (link)
- 15 April, 2022 Our tutorial "Sparse Neural Networks Training" has been accepted at ECMLPKDD 2022 (link)
- 20 January, 2022 One paper on dynamic sparse training has been accepted at ICLR 2022 (link)
Organisations
Publications
Recent
de Ranitz, A.
, Beldad, A. D.
, & Mocanu, E. (2023).
Enhancing Learning in Sparse Neural Networks: A Hebbian Learning Approach. In
BNAIC/BENELEARN 2023
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 A. Ricci, W. Yeoh, N. Agmon, & B. An (Eds.),
AAMAS '23: Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems (Vol. 2023-May, pp. 1932-1941). (Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS). ACM Press.
Xiao, Q., Zhang, Y., Liu, S., Pechenizkiy, M.
, Mocanu, E.
, & Mocanu, D. C. (2023).
Dynamic Sparse Network for Time Series Classification: Learning What to “See”. Paper presented at ICLR 2023 Workshop on Sparsity in Neural Networks, Kigali, Rwanda.
https://drive.google.com/file/d/10pxPf2aWTdMumUba_8-7v_jEZ3-K_uV3/view
Xiao, Q.
, Wu, B., Zhang, Y., Liu, S., Pechenizkiy, M.
, Mocanu, E.
, & Mocanu, D. C. (2023).
Dynamic Sparse Network for Time Series Classification: Learning What to “See”. Poster session presented at ICLR 2023 Workshop on Sparsity in Neural Networks, Kigali, Rwanda.
https://drive.google.com/file/d/10pxPf2aWTdMumUba_8-7v_jEZ3-K_uV3/view
Xiao, Q.
, Wu, B., Zhang, Y., Liu, S., Pechenizkiy, M.
, Mocanu, E.
, & Mocanu, D. C. (2022).
Dynamic Sparse Network for Time Series Classification: Learning What to “See”. Paper presented at 36th Annual Conference on Neural Information Processing Systems, NeurIPS 2022, New Orleans, Louisiana, United States.
https://openreview.net/forum?id=ZxOO5jfqSYw
Sokar, G. A. Z. N.
, Mocanu, E.
, Mocanu, D. C., Pechenizkiy, M., & Stone, P. (2022).
Dynamic Sparse Training for Deep Reinforcement Learning. In L. De Raedt (Ed.),
Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022 (pp. 3437-3443)
https://doi.org/10.24963/ijcai.2022/477
Grooten, B. J., Sokar, G.
, Mocanu, E., Dohare, S., Taylor, M. E., Pechenizkiy, M.
, & Mocanu, D. C. (2022).
Towards Implementing Truly Sparse Connections in Deep RL Agents. Poster session presented at Sparsity in Neural Networks: Advancing Understanding and Practice 2022, Virtual + ICML meetup.
Atashgahi, Z., Sokar, G., van der Lee, T.
, Mocanu, E.
, Mocanu, D. C.
, Veldhuis, R., & Pechenizkiy, M. (2022).
Quick and robust feature selection: the strength of energy-efficient sparse training for autoencoders.
Machine Learning,
111, 377–414. Advance online publication.
https://doi.org/10.1007/s10994-021-06063-x
Liu, S., Chen, T.
, Atashgahi, Z., Chen, X., Sokar, G.
, Mocanu, E., Pechenizkiy, M., Wang, Z.
, & Mocanu, D. C. (2022).
Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity. In
The Tenth International Conference on Learning Representations, ICLR 2022 OpenReview.
https://openreview.net/forum?id=RLtqs6pzj1-¬eId=d7CKVDyMGZi
Liu, S., Chen, T.
, Atashgahi, Z., Chen, X., Sokar, G. A. Z. N.
, Mocanu, E., Pechenizkiy, M., Wang, Z.
, & Mocanu, D. C. (2021).
FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity. Poster session presented at Sparsity in Neural Networks: Advancing Understanding and Practice 2021, Online.
UT Research Information System
Google Scholar Link
Courses Academic Year 2023/2024
Courses in the current academic year are added at the moment they are finalised in the Osiris system. Therefore it is possible that the list is not yet complete for the whole academic year.
Courses Academic Year 2022/2023
In the press
- 2021, Inovex GmbH, AI blog Pruning and Sparsification of Neural Networks
- 2021, Towards Data Science, Neural Network Pruning 101
- 2020, Numenta, The Case For Sparsity in Neural Networks, Part 2: Dynamic Sparsity
- 2019, TechXplore, A bio-inspired approach to enhance learning in ANNs
- 2018, Nature Collections, The multidisciplinary nature of machine intelligence
- 2018, Towards Data Science, The Sparse Future of Deep Learning
- 2018, Phys.org, New AI method increases the power of artificial neural networks
- 2018, E&T magazine, Artificial neural networks could run on cheap computers using new method
- 2018, Technologist, AI method increases the power of artificial neural networks
- 2018, Elektor magazine, Nieuw algoritme versnelt kunstmatige intelligentie kwadratisch
- 2018, EMERCE, Nieuwe AI-methode vergroot de kracht van kunstmatige neurale netwerken
- 2018, deVolkskrant, Ook het stroomnet denkt straks na
Contact Details
Visiting Address
University of Twente
Faculty of Electrical Engineering, Mathematics and Computer Science
Zilverling
(building no. 11)
Hallenweg 19
7522NH Enschede
The Netherlands
Mailing Address
University of Twente
Faculty of Electrical Engineering, Mathematics and Computer Science
Zilverling
P.O. Box 217
7500 AE Enschede
The Netherlands