Posts by Collection

Topological insights into sparse neural networks

Published in ECML PKDD 2020, European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases, 2020

Recommended citation: Liu, S., Van der Lee, T., Yaman, A., Atashgahi, Z., Ferraro, D., Sokar, G., ... & Mocanu, D. C. (2020). Topological insights into sparse neural networks. In Proceedings of European Conference on Machine Learning and Knowledge Discovery in Databases, ECML PKDD 2020, Research Track https://arxiv.org/pdf/2006.14085.pdf

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Published in Accepted at NeurIPS 2021, 2021

Recommended citation: Liu, S., Chen, T., Chen, X., Atashgahi, Z., Yin, L., Kou, H., ... & Mocanu, D. C. (2021). Sparse Training via Boosting Pruning Plasticity with Neuroregeneration. arXiv preprint arXiv:2106.10404. https://arxiv.org/pdf/2106.10404.pdf

[Extended Abstract] Unsupervised Online Memory-free Change-point Detection using an Ensemble of LSTM-Autoencoder-based Neural Networks

Published in , 2021

Extended abstract at ACMwomENcourage 2021

Recommended citation: Atashgahi, Z., Mocanu, D. C., Veldhuis, R., & Pechenizkiy, M. Unsupervised Online Memory-free Change-point Detection using an Ensemble of LSTM-Autoencoder-based Neural Networks. https://womencourage.acm.org/2021/wp-content/uploads/2021/07/65_extendedabstract.pdf

Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders

Published in In Press: Machine Learning (ECML-PKDD 2022 journal track), 2022

Feature selection using sparse neural networks

Recommended citation: 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(1), 377-414. https://arxiv.org/abs/2012.00560

Deep Ensembling with No Overhead for either Training or Testing: The All-Round Blessings of Dynamic Sparsity

Published in International Conference on Learning Representations (ICLR 2022), 2022

Recommended citation: Liu, S., Chen, T., Atashgahi, Z., Chen, X., Sokar, G., Mocanu, E., ... & Mocanu, D. C. (2021). FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity. arXiv preprint arXiv:2106.14568. https://arxiv.org/pdf/2106.14568.pdf

A Brain-inspired Algorithm for Training Highly Sparse Neural Networks

Published in Accepted for publication at Machine Learning Journal - ECML PKDD Journal track, 2022

Training highly sparse neural networks

Recommended citation: Atashgahi, Z., Pieterse, J., Liu, S., Mocanu, D. C., Veldhuis, R., & Pechenizkiy, M. (2022). A Brain-inspired Algorithm for Training Highly Sparse Neural Networks. arXiv preprint arXiv:1903.07138. https://arxiv.org/abs/1903.07138

Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders

Published: November 12, 2021

I’ve presented our paper “Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders” at University of Luxembourg at BNAIC/BENELEARN 2021. Find more information here. (paper, code)

A Brain-inspired Algorithm for Training Highly Sparse Neural Networks

Published: April 28, 2022

I’ve presented our paper “A Brain-inspired Algorithm for Training Highly Sparse Neural Networks” at Eindhoven University of Technology at ICLR 2022 local event. Find more information here. (paper, code)

Sparse Neural Networks Training

Published: September 23, 2022

More information here

Learning Efficiently from Data using Sparse Neural Networks

Published: March 10, 2023

More information here