Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Shiwei Liu

Hierarchical Semantic Segmentation using Psychometric Learning


Jul 07, 2021
Lu Yin, Vlado Menkovski, Shiwei Liu, Mykola Pechenizkiy

* 17 pages, 12 figures 

  Access Paper or Ask Questions

FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity


Jun 28, 2021
Shiwei Liu, Tianlong Chen, Zahra Atashgahi, Xiaohan Chen, Ghada Sokar, Elena Mocanu, Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu

* preprint version 

  Access Paper or Ask Questions

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration


Jun 19, 2021
Shiwei Liu, Tianlong Chen, Xiaohan Chen, Zahra Atashgahi, Lu Yin, Huanyu Kou, Li Shen, Mykola Pechenizkiy, Zhangyang Wang, Decebal Constantin Mocanu


  Access Paper or Ask Questions

Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training


Feb 13, 2021
Shiwei Liu, Lu Yin, Decebal Constantin Mocanu, Mykola Pechenizkiy

* 15 pages, 9 figures, preprint version 

  Access Paper or Ask Questions

Selfish Sparse RNN Training


Jan 28, 2021
Shiwei Liu, Decebal Constantin Mocanu, Yulong Pei, Mykola Pechenizkiy

* 19 pages,10 figures 

  Access Paper or Ask Questions

Topological Insights into Sparse Neural Networks


Jul 04, 2020
Shiwei Liu, Tim Van der Lee, Anil Yaman, Zahra Atashgahi, Davide Ferraro, Ghada Sokar, Mykola Pechenizkiy, Decebal Constantin Mocanu

* 17 pages, 17 pages 

  Access Paper or Ask Questions

Topological Insights in Sparse Neural Networks


Jun 24, 2020
Shiwei Liu, Tim Van der Lee, Anil Yaman, Zahra Atashgahi, Davide Ferraro, Ghada Sokar, Mykola Pechenizkiy, Decebal Constantin Mocanu

* 17 pages, 17 pages 

  Access Paper or Ask Questions

On improving deep learning generalization with adaptive sparse connectivity


Jun 27, 2019
Shiwei Liu, Decebal Constantin Mocanu, Mykola Pechenizkiy

* ICML 2019 Workshop on Understanding and Improving Generalization in Deep Learning 

  Access Paper or Ask Questions

Intrinsically Sparse Long Short-Term Memory Networks


Jan 26, 2019
Shiwei Liu, Decebal Constantin Mocanu, Mykola Pechenizkiy

* 9 pages, 8 figures and 4 tables 

  Access Paper or Ask Questions

Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware


Jan 26, 2019
Shiwei Liu, Decebal Constantin Mocanu, Amarsagar Reddy Ramapuram Matavalam, Yulong Pei, Mykola Pechenizkiy

* 14 pages 

  Access Paper or Ask Questions