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

Shiwei Liu

Hierarchical Semantic Segmentation using Psychometric Learning


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

Figure 1 for Hierarchical Semantic Segmentation using Psychometric Learning
Figure 2 for Hierarchical Semantic Segmentation using Psychometric Learning
Figure 3 for Hierarchical Semantic Segmentation using Psychometric Learning
Figure 4 for Hierarchical Semantic Segmentation using Psychometric Learning
* 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

Figure 1 for FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity
Figure 2 for FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity
Figure 3 for FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity
Figure 4 for FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity
* 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

Figure 1 for Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Figure 2 for Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Figure 3 for Sparse Training via Boosting Pruning Plasticity with Neuroregeneration
Figure 4 for Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

  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

Figure 1 for Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Figure 2 for Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Figure 3 for Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
Figure 4 for Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training
* 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

Figure 1 for Selfish Sparse RNN Training
Figure 2 for Selfish Sparse RNN Training
Figure 3 for Selfish Sparse RNN Training
Figure 4 for Selfish Sparse RNN Training
* 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

Figure 1 for Topological Insights into Sparse Neural Networks
Figure 2 for Topological Insights into Sparse Neural Networks
Figure 3 for Topological Insights into Sparse Neural Networks
Figure 4 for Topological Insights into Sparse Neural Networks
* 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

Figure 1 for Topological Insights in Sparse Neural Networks
Figure 2 for Topological Insights in Sparse Neural Networks
Figure 3 for Topological Insights in Sparse Neural Networks
Figure 4 for Topological Insights in Sparse Neural Networks
* 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

Figure 1 for On improving deep learning generalization with adaptive sparse connectivity
Figure 2 for On improving deep learning generalization with adaptive sparse connectivity
Figure 3 for On improving deep learning generalization with adaptive sparse connectivity
Figure 4 for On improving deep learning generalization with adaptive sparse connectivity
* 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

Figure 1 for Intrinsically Sparse Long Short-Term Memory Networks
Figure 2 for Intrinsically Sparse Long Short-Term Memory Networks
Figure 3 for Intrinsically Sparse Long Short-Term Memory Networks
Figure 4 for Intrinsically Sparse Long Short-Term Memory Networks
* 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

Figure 1 for Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
Figure 2 for Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
Figure 3 for Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
Figure 4 for Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware
* 14 pages 
  Access Paper or Ask Questions