Deep Neural Network

DNN training for LibSVM-formatted data - From Keras to Estimator

This article provides a fully verified solution (with code) to run LR and GBDT on a LibSVM-formatted dataset efficiently using TensorFlow.

Alibaba Cloud DFSMN Breaks the Barriers of Speech Recognition Accuracy with MaxCompute

Alibaba Cloud makes its high-accuracy speech recognition model (96.04%), Deep Feedforward Sequential Memory Network (DFSMN), open source on GitHub.