no code implementations • 16 Oct 2021 • Shehryar Malik, Muhammad Umair Haider, Omer Iqbal, Murtaza Taj
In this work, we propose a general methodology for pruning neural networks.
no code implementations • 6 Oct 2020 • Muhammad Umair Haider, Murtaza Taj
One of the major challenges in deploying deep neural network architectures is their size which has an adverse effect on their inference time and memory requirements.
2 code implementations • 7 Apr 2020 • Shaiq Munir Malik, Muhammad Umair Haider, Mohbat Tharani, Musab Rasheed, Murtaza Taj
To reduce the overwhelming size of Deep Neural Networks (DNN) teacher-student methodology tries to transfer knowledge from a complex teacher network to a simple student network.