23 citations · 48 across the 11 of their papers we have counts for
4 papers · 1 filter
Measure, Manifold, Learning, and Optimization: A Theory Of Neural Networks
Shuai Li
We present a formal measure-theoretical theory of neural networks (NN) built on probability coupling theory. Our main contributions are summarized as follows. * Built on the formal…
Learning to synthesize: splitting and recombining low and high spatial frequencies for image recovery
Mo Deng, Shuai Li, George Barbastathis
Deep Neural Network (DNN)-based image reconstruction, despite many successes, often exhibits uneven fidelity between high and low spatial frequency bands. In this paper we propose…
Gear Training: A new way to implement high-performance model-parallel training
Hao Dong, Shuai Li, Dongchang Xu +2
The training of Deep Neural Networks usually needs tremendous computing resources. Therefore many deep models are trained in large cluster instead of single machine or GPU. Though…
Independently Recurrent Neural Network (IndRNN): Building A Longer and Deeper RNN
Shuai Li, Wanqing Li, Chris Cook +2
Recurrent neural networks (RNNs) have been widely used for processing sequential data. However, RNNs are commonly difficult to train due to the well-known gradient vanishing and ex…