Differential Recurrent Neural Network and its Application for Human Activity Recognition

no code implementations • 9 May 2019 • Naifan Zhuang, Guo-Jun Qi, The Duc Kieu, Kien A. Hua

The Long Short-Term Memory (LSTM) recurrent neural network is capable of processing complex sequential information since it utilizes special gating schemes for learning representations from long input sequences.

Human Activity Recognition Time Series +1

Deep Differential Recurrent Neural Networks

no code implementations • 11 Apr 2018 • Naifan Zhuang, The Duc Kieu, Guo-Jun Qi, Kien A. Hua

The proposed model progressively builds up the ability of the LSTM gates to detect salient dynamical patterns in deeper stacked layers modeling higher orders of DoS, and thus the proposed LSTM model is termed deep differential Recurrent Neural Network (d2RNN).

Temporal Sequences