M
Mark Z. Mao
Researcher at Google
Publications - 11
Citations - 5080
Mark Z. Mao is an academic researcher from Google. The author has contributed to research in topics: Deep learning & Artificial neural network. The author has an hindex of 6, co-authored 11 publications receiving 4577 citations. Previous affiliations of Mark Z. Mao include Stanford University.
Papers
More filters
Proceedings Article
Large Scale Distributed Deep Networks
Jeffrey Dean,Greg S. Corrado,Rajat Monga,Kai Chen,Matthieu Devin,Mark Z. Mao,Marc'Aurelio Ranzato,Andrew W. Senior,Paul A. Tucker,Ke Yang,Quoc V. Le,Andrew Y. Ng +11 more
TL;DR: This paper considers the problem of training a deep network with billions of parameters using tens of thousands of CPU cores and develops two algorithms for large-scale distributed training, Downpour SGD and Sandblaster L-BFGS, which increase the scale and speed of deep network training.
Improving the speed of neural networks on CPUs
TL;DR: This paper uses speech recognition as an example task, and shows that a real-time hybrid hidden Markov model / neural network (HMM/NN) large vocabulary system can be built with a 10× speedup over an unoptimized baseline and a 4× speed up over an aggressively optimized floating-point baseline at no cost in accuracy.
Proceedings ArticleDOI
On rectified linear units for speech processing
Matthew D. Zeiler,Marc'Aurelio Ranzato,Rajat Monga,Mark Z. Mao,Ke Yang,Quoc V. Le,Patrick Nguyen,Andrew W. Senior,Vincent Vanhoucke,Jeffrey Dean,Geoffrey E. Hinton +10 more
TL;DR: This work shows that it can improve generalization and make training of deep networks faster and simpler by substituting the logistic units with rectified linear units.
Proceedings ArticleDOI
Sequence Discriminative Distributed Training of Long Short-Term Memory Recurrent Neural Networks
Hasim Sak,Oriol Vinyals,Georg Heigold,Andrew W. Senior,Erik McDermott,Rajat Monga,Mark Z. Mao +6 more
TL;DR: This paper compares two sequence discriminative criteria – maximum mutual information and state-level minimum Bayes risk, and investigates a number of variations of the basic training strategy to better understand issues raised by both the sequential model, and the objective function.
Journal ArticleDOI
Rate-Constrained Simulation and Source Coding i.i.d. Sources
TL;DR: Experimental evidence shows that the approach provides comparable or superior performance in comparison with previously published methods on common examples, sometimes by significant margins.