WALKING WALKing walking: Action Recognition from Action Echoes

Shen, Lifeng; Chen, Enhuan; Tian, Sufang; Wang, Jiabing; Cottrell, Garrison W.

doi:10.24963/ijcai.2017/342

Cited by 20 publications

(22 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results of our work show the promise of deep learning methods such as RC-ESNs (and to some extent RNN-LSTM) for data-driven modeling of chaotic dynamical systems, which has broad applications in geosciences, e.g., in weather/climate modeling. Practical and fundamental issues such as interpretability, scalability to higher dimensional systems [43], presence of measurement noise in the training data and initial conditions [44], non-stationarity of the time series, and dealing with data that have two or three spatial dimensions (e.g., through integration with convolutional neural networks, CNN-LSTM [80] and CNN-ESN [81] should be studied in future work.…”

Section: Discussionmentioning

confidence: 99%

Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM

Chattopadhyay¹,

Hassanzadeh²,

Subramanian³

2019

Preprint

View full text Add to dashboard Cite

In this paper, the performance of three deep learning methods for predicting short-term evolution and for reproducing the long-term statistics of a multi-scale spatio-temporal Lorenz 96 system is examined. The methods are: echo state network (a type of reservoir computing, RC-ESN), deep feed-forward artificial neural network (ANN), and recurrent neural network with long short-term memory (RNN-LSTM). This Lorenz 96 system has three tiers of nonlinearly interacting variables representing slow/largescale (X), intermediate (Y ), and fast/small-scale (Z) processes. For training or testing, only X is available; Y and Z are never known or used. We show that RC-ESN substantially outperforms ANN and RNN-LSTM for short-term prediction, e.g., accurately forecasting the chaotic trajectories for hundreds of numerical solver's time steps, equivalent to several Lyapunov timescales. The RNN-LSTM and ANN show some prediction skills as well; RNN-LSTM bests ANN. Furthermore, even after losing the trajectory, data predicted by RC-ESN and RNN-LSTM have probability density functions (PDFs) that closely match the true PDF, even at the tails. The PDF of the data predicted using ANN, however, deviates from the true PDF. Implications, caveats, and applications to data-driven and data-assisted surrogate modeling of complex nonlinear dynamical systems such as weather/climate are discussed.

show abstract

Section: Discussionmentioning

confidence: 99%

Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM

Chattopadhyay¹,

Hassanzadeh²,

Subramanian³

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…The results of our work show the promise of deep learning methods such as RC-ESNs (and to some extent RNN-LSTM) for data-driven modeling of chaotic dynamical systems, which has broad applications in studies of natural and engineering systems. Practical and fundamental issues such as interpretability, scalability to higher dimensional systems [37], presence of measurement noise in the training data and initial conditions [38], non-stationarity of the time series, and dealing with data that have two or three spatial dimensions (e.g., through integration with convolutional neural networks, CNN-LSTM [74] and CNN-ESN [75]) should be studied in future work.…”

Section: Discussionmentioning

confidence: 99%

Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM

Chattopadhyay¹,

Hassanzadeh²,

Subramanian³

2020

Preprint

View full text Add to dashboard Cite

Abstract. In this paper, the performance of three deep learning methods for predicting short-term evolution and for reproducing the long-term statistics of a multi-scale spatio-temporal Lorenz 96 system is examined. The methods are: echo state network (a type of reservoir computing, RC-ESN), deep feed-forward artificial neural network (ANN), and recurrent neural network with long short-term memory (RNN-LSTM). This Lorenz 96 system has three tiers of nonlinearly interacting variables representing slow/large-scale (X), intermediate (Y), and fast/small-scale (Z) processes. For training or testing, only X is available; Y and Z are never known or used. We show that RC-ESN substantially outperforms ANN and RNN-LSTM for short-term prediction, e.g., accurately forecasting the chaotic trajectories for hundreds of numerical solver's time steps, equivalent to several Lyapunov timescales. The RNN-LSTM and ANN show some prediction skills as well; RNN-LSTM bests ANN. Furthermore, even after losing the trajectory, data predicted by RC-ESN and RNN-LSTM have probability density functions (PDFs) that closely match the true PDF, even at the tails. The PDF of the data predicted using ANN, however, deviates from the true PDF. Implications, caveats, and applications to data-driven and data-assisted surrogate modeling of complex nonlinear dynamical systems such as weather/climate are discussed.

show abstract

“…• Echo State Property (ESP) [15], [36]: The ESP means that inputs with more similar short-term history will evoke closer echo states, which ensure the dynamical stability of the reservoir. ESP also provides the ESNs an important capability called ''fading memory'' or ''shortterm memory.''…”

Section: Echo State Networkmentioning

confidence: 99%

Long-Short Term Echo State Network for Time Series Prediction

Zheng

Xiao

et al. 2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

The Echo State Networks (ESNs) is an efficient recurrent neural network consisting of a randomly generated reservoir (a large number of neurons with sparse random recurrent connections) and a trainable linear layer. It has received widespread attention for its simplicity and effectiveness, especially for time series prediction tasks. However, there is no explicit mechanism in ESNs to capture the inherent multiscale characteristics of time series. To this end, we propose a model consisting of multi-reservoir structure named long-short term echo state networks (LS-ESNs) to capture the multi-scale temporal characteristics of time series. Specifically, LS-ESNs consists of three independent reservoirs, and each reservoir has recurrent connections of a specific timescale to model the temporal dependencies of time series. The multi-scale echo states are then collected from each reservoir and concatenated together. Finally, the concatenated echo states representations are fed to the linear regression layer to obtain the results. Experiments on two time series prediction benchmark data sets and a real-world power load data sets demonstrate the effectiveness of the proposed LS-ESNs. INDEX TERMS Time series prediction, echo state networks (ESNs), multi-scale temporal dependencies, long short term reservoir.

show abstract

WALKING WALKing walking: Action Recognition from Action Echoes

Cited by 20 publications

References 14 publications

Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM

Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM

Data-driven prediction of a multi-scale Lorenz 96 chaotic system using deep learning methods: Reservoir computing, ANN, and RNN-LSTM

Long-Short Term Echo State Network for Time Series Prediction

Contact Info

Product

Resources

About