John Tran — accepted AI-conference papers

2017

DSD: Dense-Sparse-Dense Training for Deep Neural Networks

Song Han, Jeff Pool, Sharan Narang, Huizi Mao, Enhao Gong, Shijian Tang +6

ICLR 2017poster

Modern deep neural networks have a large number of parameters, making them very hard to train. We propose DSD, a dense-sparse-dense training flow, for regularizing deep neural networks and achieving better optimization performance. In the first D (Dense) step, we train a dense network to learn conne…

Cited by 265 Source ↗code ↗Scholar ↗

2015

Learning both Weights and Connections for Efficient Neural Network

Song Han, Jeff Pool, John Tran, William Dally

NeurIPS 2015poster

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems. Also, conventional networks fix the architecture before training starts; as a result, training cannot improve the architecture. To address these limitations, we describe a me…

Cited by 8960 Source ↗PDF ↗Scholar ↗