22 citations · 61 across the 30 of their papers we have counts for
Showing 2016Show all
2 papers · 1 filter
cs.DC2016★ 1 cited
Optimizing Memory Efficiency for Deep Convolutional Neural Networks on GPUs
Chao Li, Yi Yang, Min Feng +2
Leveraging large data sets, deep Convolutional Neural Networks (CNNs) achieve state-of-the-art recognition accuracy. Due to the substantial compute and memory operations, however,…
cs.LG2016★ 7 cited
Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent
Linnan Wang, Yi Yang, Martin Renqiang Min +1
SGD is the widely adopted method to train CNN. Conceptually it approximates the population with a randomly sampled batch; then it evenly trains batches by conducting a gradient upd…