11 citations · 12 across the 2 of their papers we have counts for
3 papers
cs.CV2019★ 11 cited
CGaP: Continuous Growth and Pruning for Efficient Deep Learning
Xiaocong Du, Zheng Li, Yu Cao
Today a canonical approach to reduce the computation cost of Deep Neural Networks (DNNs) is to pre-define an over-parameterized model before training to guarantee the learning capa…
cs.NE2019★ 1 cited
Towards Efficient Neural Networks On-a-chip: Joint Hardware-Algorithm Approaches
Xiaocong Du, Gokul Krishnan, Abinash Mohanty +3
Machine learning algorithms have made significant advances in many applications. However, their hardware implementation on the state-of-the-art platforms still faces several challe…
cs.NE2019
Efficient Network Construction through Structural Plasticity
Xiaocong Du, Zheng Li, Yufei Ma +1
Deep Neural Networks (DNNs) on hardware is facing excessive computation cost due to the massive number of parameters. A typical training pipeline to mitigate over-parameterization…