Hybrid Neural Networks for
Time Series Learning
Tian Guo
Ph.D.
24 Nov. 2016
Outline
• Introduction
• Hybrid Neural Network (HNN)
• HNN for Real
• Preliminaries
• TreNet: a HNN for learning the local trend of time series
• Experiment results
• Conclusion
2
Introduction
3Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Introduction
• Time series data: a sequence of data points consisting of
successive measurements made over time.
• Internet of Things
• Sensor networks
• Mobile phones
• And more…
4Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Introduction
• Time series analytics in a variety of applications
• Classification
• Prediction
• Anomaly detection
• Pattern discovery
• And more…
5
Pattern 1 Pattern 2
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Introduction
• Time series analytics tools
• Statistics
• Hidden Markov Model (HMM)
• State Space Model
• ARIMA
• Machine learning
• Random Forest
• SVM
• Gaussian Process
•
6
Random Forest
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Introduction
• Neural Network and Deep Learning
• Language translation
• E.g., Google’s Multilingual Neural Machine Translation System
• Computer vision
• E.g., Microsoft Research’s PReLU network outperforms Human-Level
performance on ImageNet Classification
• Speech recognition
• E.g., Amazon Echo, Apple Siri
• Time series classification
• E.g. recognize patterns in multivariate
time series of clinical measurements
7
Z. Lipton, et al. “Learning to Diagnose with LSTM Recurrent Neural Networks”. ICLR, 2016.
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Introduction
• Fundamental network architectures
• Convolutional neural network: input two-dimensional data, e.g.,
image
• Recurrent neural network: input
8
Unfolded recurrent connections in a RNN
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Introduction
• Convolutional Neural Network (CNN)
• Feature learning for images
• To extract high-level features from raw data
• Such high-level features are further used for classification or
regression.
9
K. He, et al. “Delving deep into rectifiers: Surpassing Human-Level Performance on ImageNet Classification”. arxiv.org, 2015
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Introduction
• Convolutional Neural Network (CNN)
• CNN in the Human Activity Recognition Problem
• Multichannel time series acquired from a set of body-worn sensors
• To predict human activities by training a CNN over time series
10
J. Yang, et al. “Deep Convolutional Neural Networks On Multichannel Time Series For Human Activity Recognition”. IJCAI 2015
Value
Time
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Introduction
• Recurrent Neural Network (RNN)
• A powerful tool to model sequence data
• To capture dependency in sequence data
• Long-short term memory network (LSTM)
• A widely used variant of RNNs
• Equipped with memory and gate mechanism
• To overcome gradient vanishing and explosion
11
S. Hochreiter, et al. “Long short-term memory’’. Neural computation, 1997.
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
12Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
• CNN or RNN
• Work well for respective data, i.e. images and sequence data
13Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
• A cascade of CNN and RNN
• Classification of EEG data
• Electroencephalogram (EEG) : multiple time series corresponding to
measurements across different spatial locations over the cortex.
• Mental load classification task:
measures the working memory
responsible for transient retention
of information in the brain.
14
P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
• A cascade of CNN and RNN
• Classification of EEG data
• A key challenge in correctly recognizing mental states
• EEG data often contains translation
and deformation of signal in space,
frequency, and time, due to inter-
and intra-subject differences
15
P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
• A cascade of CNN and RNN
• Classification of EEG data
16
P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
• A cascade of CNN and RNN
• EEG data classification
17
P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
• Time Series
• Noisy
• Non-stationary
• Hidden information: states, dynamics
• Auto-correlated on the temporal dimension
• Manual feature engineering
• Preprocessing: de-trending, outlier removal, etc.
• Dimension reduction: Fourier Transformation
• Piecewise approximation: PAA, PCA, PLA, etc.
• Application-specific, domain knowledge
18
Why do we need hybrid architectures?
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
• Hybrid architectures: end-to-end learning framework
• Loss function driven training
• Learning representative features
• Capturing sequential dependency in data
19
Why do we need hybrid architectures?
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Hybrid Neural Networks
• A cascade of CNN and RNN
20
P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
HNN for Real:
TreNet for Learning the Local Trend
21
T. Guo, et al. TreNet: Hybrid Neural Networks for Learning the Local Trend in Temporal Data. In submission to ICLR, 2017
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Preliminaries
• Conventional trend analysis in time series
is the seasonal component at time t
is the trend component at t
is the remainder
22Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Preliminaries
• Local trend
• Measure the intermediate local behaviour, i.e. upward or downward
pattern of time series
• For instance, the time series of household power consumption and
the local trends are shown as follows:
• Time series
• Extracted local trend ,
is the duration and is the slope
23Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Preliminaries
• Learning and forecasting the local trend
• Predict ,
• Useful in many applications
• Smart energy
• Stock market
• And more …
24Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Preliminaries
• Learning and forecasting the local trend
• Local raw data
• Global contextual information
in the historical sequence of trend
• To learn a function
is either or
25Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
TreNet
• Overview of TreNet
• is derived by training the LSTM over sequence to
capture the dependency in the trend evolving.
• corresponds to local features extracted by CNN from
26Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
is derived by training the LSTM over sequence to capture
the dependency in the trend evolving.
corresponds to local features extracted by CNN from
TreNet
• Overview
•
27Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
TreNet
• Learning
28Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
TreNet
• LSTM
• Feed the sequence of
• Output
29Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
TreNet
• CNN
• Output
30Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
TreNet
• Feature Fusion and output layers
31Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
TreNet
• Learning
• Gradient descent
32Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Experiments
• Datasets
• Daily Household Power Consumption (HousePC)
• Gas Sensor (GasSensor)
• Stock Transaction (Stock)
33
E Keogh, et al. “An online algorithm for segmenting time series”. ICDM, 2001
Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Experiments
• Baselines
• CNN
• LSTM
• Support Vector Regression (SVR)
• Radial Basis kernel (SVRBF)
• Polynomial kernel (SVPOLY)
• Sigmoid kernel (SVSIG)
• Pattern-based Hidden Markov Model (pHMM)
34Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
P. Wang, et al. “Finding Semantics in Time Series”, SIGMOD 2011
Experiments
• Results: overall accuracy
35Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Experiments
• Results: prediction visualization
36Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
Conclusion
37
Conclusion
38
• Hybrid neural networks
• TreNet for the Local Trend Learning
• Future work: a generic idea
• Social media streams
• Heterogeneous data
• Influence analysis
• And more…
Thanks! Q & A
This work is supported by EU OpenIoT Project
(Open Source Solution for the Internet of Things)
http://www.openiot.eu/
Feel free to contact: tian.guo0980@gmail.com, tian.guo@epfl.ch

Hybrid neural networks for time series learning by Tian Guo, EPFL, Switzerland

  • 1.
    Hybrid Neural Networksfor Time Series Learning Tian Guo Ph.D. 24 Nov. 2016
  • 2.
    Outline • Introduction • HybridNeural Network (HNN) • HNN for Real • Preliminaries • TreNet: a HNN for learning the local trend of time series • Experiment results • Conclusion 2
  • 3.
    Introduction 3Introduction Hybrid NeuralNetwork(HNN) TreNet for Local Trend
  • 4.
    Introduction • Time seriesdata: a sequence of data points consisting of successive measurements made over time. • Internet of Things • Sensor networks • Mobile phones • And more… 4Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 5.
    Introduction • Time seriesanalytics in a variety of applications • Classification • Prediction • Anomaly detection • Pattern discovery • And more… 5 Pattern 1 Pattern 2 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 6.
    Introduction • Time seriesanalytics tools • Statistics • Hidden Markov Model (HMM) • State Space Model • ARIMA • Machine learning • Random Forest • SVM • Gaussian Process • 6 Random Forest Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 7.
    Introduction • Neural Networkand Deep Learning • Language translation • E.g., Google’s Multilingual Neural Machine Translation System • Computer vision • E.g., Microsoft Research’s PReLU network outperforms Human-Level performance on ImageNet Classification • Speech recognition • E.g., Amazon Echo, Apple Siri • Time series classification • E.g. recognize patterns in multivariate time series of clinical measurements 7 Z. Lipton, et al. “Learning to Diagnose with LSTM Recurrent Neural Networks”. ICLR, 2016. Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 8.
    Introduction • Fundamental networkarchitectures • Convolutional neural network: input two-dimensional data, e.g., image • Recurrent neural network: input 8 Unfolded recurrent connections in a RNN Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 9.
    Introduction • Convolutional NeuralNetwork (CNN) • Feature learning for images • To extract high-level features from raw data • Such high-level features are further used for classification or regression. 9 K. He, et al. “Delving deep into rectifiers: Surpassing Human-Level Performance on ImageNet Classification”. arxiv.org, 2015 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 10.
    Introduction • Convolutional NeuralNetwork (CNN) • CNN in the Human Activity Recognition Problem • Multichannel time series acquired from a set of body-worn sensors • To predict human activities by training a CNN over time series 10 J. Yang, et al. “Deep Convolutional Neural Networks On Multichannel Time Series For Human Activity Recognition”. IJCAI 2015 Value Time Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 11.
    Introduction • Recurrent NeuralNetwork (RNN) • A powerful tool to model sequence data • To capture dependency in sequence data • Long-short term memory network (LSTM) • A widely used variant of RNNs • Equipped with memory and gate mechanism • To overcome gradient vanishing and explosion 11 S. Hochreiter, et al. “Long short-term memory’’. Neural computation, 1997. Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 12.
    Hybrid Neural Networks 12IntroductionHybrid Neural Network(HNN) TreNet for Local Trend
  • 13.
    Hybrid Neural Networks •CNN or RNN • Work well for respective data, i.e. images and sequence data 13Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 14.
    Hybrid Neural Networks •A cascade of CNN and RNN • Classification of EEG data • Electroencephalogram (EEG) : multiple time series corresponding to measurements across different spatial locations over the cortex. • Mental load classification task: measures the working memory responsible for transient retention of information in the brain. 14 P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 15.
    Hybrid Neural Networks •A cascade of CNN and RNN • Classification of EEG data • A key challenge in correctly recognizing mental states • EEG data often contains translation and deformation of signal in space, frequency, and time, due to inter- and intra-subject differences 15 P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 16.
    Hybrid Neural Networks •A cascade of CNN and RNN • Classification of EEG data 16 P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 17.
    Hybrid Neural Networks •A cascade of CNN and RNN • EEG data classification 17 P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 18.
    Hybrid Neural Networks •Time Series • Noisy • Non-stationary • Hidden information: states, dynamics • Auto-correlated on the temporal dimension • Manual feature engineering • Preprocessing: de-trending, outlier removal, etc. • Dimension reduction: Fourier Transformation • Piecewise approximation: PAA, PCA, PLA, etc. • Application-specific, domain knowledge 18 Why do we need hybrid architectures? Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 19.
    Hybrid Neural Networks •Hybrid architectures: end-to-end learning framework • Loss function driven training • Learning representative features • Capturing sequential dependency in data 19 Why do we need hybrid architectures? Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 20.
    Hybrid Neural Networks •A cascade of CNN and RNN 20 P. Bashivan, et. al. “Learning Representations from EEG with Deep Recurrent-Convolutional Neural Networks”. ICLR, 2016 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 21.
    HNN for Real: TreNetfor Learning the Local Trend 21 T. Guo, et al. TreNet: Hybrid Neural Networks for Learning the Local Trend in Temporal Data. In submission to ICLR, 2017 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 22.
    Preliminaries • Conventional trendanalysis in time series is the seasonal component at time t is the trend component at t is the remainder 22Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 23.
    Preliminaries • Local trend •Measure the intermediate local behaviour, i.e. upward or downward pattern of time series • For instance, the time series of household power consumption and the local trends are shown as follows: • Time series • Extracted local trend , is the duration and is the slope 23Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 24.
    Preliminaries • Learning andforecasting the local trend • Predict , • Useful in many applications • Smart energy • Stock market • And more … 24Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 25.
    Preliminaries • Learning andforecasting the local trend • Local raw data • Global contextual information in the historical sequence of trend • To learn a function is either or 25Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 26.
    TreNet • Overview ofTreNet • is derived by training the LSTM over sequence to capture the dependency in the trend evolving. • corresponds to local features extracted by CNN from 26Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 27.
    is derived bytraining the LSTM over sequence to capture the dependency in the trend evolving. corresponds to local features extracted by CNN from TreNet • Overview • 27Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 28.
    TreNet • Learning 28Introduction HybridNeural Network(HNN) TreNet for Local Trend
  • 29.
    TreNet • LSTM • Feedthe sequence of • Output 29Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 30.
    TreNet • CNN • Output 30IntroductionHybrid Neural Network(HNN) TreNet for Local Trend
  • 31.
    TreNet • Feature Fusionand output layers 31Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 32.
    TreNet • Learning • Gradientdescent 32Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 33.
    Experiments • Datasets • DailyHousehold Power Consumption (HousePC) • Gas Sensor (GasSensor) • Stock Transaction (Stock) 33 E Keogh, et al. “An online algorithm for segmenting time series”. ICDM, 2001 Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 34.
    Experiments • Baselines • CNN •LSTM • Support Vector Regression (SVR) • Radial Basis kernel (SVRBF) • Polynomial kernel (SVPOLY) • Sigmoid kernel (SVSIG) • Pattern-based Hidden Markov Model (pHMM) 34Introduction Hybrid Neural Network(HNN) TreNet for Local Trend P. Wang, et al. “Finding Semantics in Time Series”, SIGMOD 2011
  • 35.
    Experiments • Results: overallaccuracy 35Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 36.
    Experiments • Results: predictionvisualization 36Introduction Hybrid Neural Network(HNN) TreNet for Local Trend
  • 37.
  • 38.
    Conclusion 38 • Hybrid neuralnetworks • TreNet for the Local Trend Learning • Future work: a generic idea • Social media streams • Heterogeneous data • Influence analysis • And more…
  • 39.
    Thanks! Q &A This work is supported by EU OpenIoT Project (Open Source Solution for the Internet of Things) http://www.openiot.eu/ Feel free to contact: tian.guo0980@gmail.com, tian.guo@epfl.ch