most citedCGaP: Continuous Growth and Pruning for Efficient Deep Learning

11 citations · 17 across the 3 of their papers we have counts for

collaborators

5 papers

cs.LG20195 cited

Structural Pruning in Deep Neural Networks: A Small-World Approach

Gokul Krishnan, Xiaocong Du, Yu Cao

Deep Neural Networks (DNNs) are usually over-parameterized, causing excessive memory and interconnection cost on the hardware platform. Existing pruning approaches remove secondary…

cs.CV201911 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.NE20191 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.LG2019

Single-Net Continual Learning with Progressive Segmented Training (PST)

Xiaocong Du, Gouranga Charan, Frank Liu +1

There is an increasing need of continual learning in dynamic systems, such as the self-driving vehicle, the surveillance drone, and the robotic system. Such a system requires learn…

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…