Transfer learning for time series classification

Abstract

Transfer learning for deep neural networks is the process of first training a base network on a source dataset, and then transferring the learned features (the network's weights) to a second network to be trained on a target dataset. This idea has been shown to improve deep neural network's generalization capabilities in many computer vision tasks such as image recognition and object localization. Apart from these applications, deep Convolutional Neural Networks (CNNs) have also recently gained popularity in the Time Series Classification (TSC) community. However, unlike for image recognition problems, transfer learning techniques have not yet been investigated thoroughly for the TSC task. This is surprising as the accuracy of deep learning models for TSC could potentially be improved if the model is fine-tuned from a pre-trained neural network instead of training it from scratch. In this paper, we fill this gap by investigating how to transfer deep CNNs for the TSC task. To evaluate the potential of transfer learning, we performed extensive experiments using the UCR archive which is the largest publicly available TSC benchmark containing 85 datasets. For each dataset in the archive, we pre-trained a model and then fine-tuned it on the other datasets resulting in 7140 different deep neural networks. These experiments revealed that transfer learning can improve or degrade the model's predictions depending on the dataset used for transfer. Therefore, in an effort to predict the best source dataset for a given target dataset, we propose a new method relying on Dynamic Time Warping to measure inter-datasets similarities. We describe how our method can guide the transfer to choose the best source dataset leading to an improvement in accuracy on 71 out of 85 datasets.

arXiv commentAccepted at IEEE International Conference on Big Data 2018

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks
• TensorFlow: A system for large-scale machine learning
• How transferable are features in deep neural networks?
• Deep learning for time series classification: a review
• Learning Transferable Features with Deep Adaptation Networks
• Multi-Scale Convolutional Neural Networks for Time Series Classification
• Domain Adaptation for Visual Applications: A Comprehensive Survey
• Deep Learning for Time-Series Analysis
• Towards a universal neural network encoder for time series
• Data augmentation using synthetic data for time series classification with deep residual networks
• Spatio-Temporal Neural Networks for Space-Time Series Forecasting and Relations Discovery
• Cost-Sensitive Convolution based Neural Networks for Imbalanced Time-Series Classification

Cited by in corpus (29)

• Deep learning for time series classification: a review
• InceptionTime: Finding AlexNet for Time Series Classification
• An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks
• Deep Learning for Time Series Forecasting: Tutorial and Literature Survey
• Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx
• A Survey of Human Activity Recognition in Smart Homes Based on IoT Sensors Algorithms: Taxonomies, Challenges, and Opportunities with Deep Learning
• Deep Transfer Learning Based Intrusion Detection System for Electric Vehicular Networks
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• Accurate and interpretable evaluation of surgical skills from kinematic data using fully convolutional neural networks
• Deep Neural Network Ensembles for Time Series Classification
• Intra-domain and cross-domain transfer learning for time series data -- How transferable are the features?
• A Transfer Learning Evaluation of Deep Neural Networks for Image Classification
• Label-efficient Time Series Representation Learning: A Review
• AdaRNN: Adaptive Learning and Forecasting of Time Series
• Similarity Learning based Few Shot Learning for ECG Time Series Classification
• Recent Advances in Named Entity Recognition: A Comprehensive Survey and Comparative Study
• Multi-source Transfer Learning with Ensemble for Financial Time Series Forecasting
• Voice2Series: Reprogramming Acoustic Models for Time Series Classification
• Data Augmentation Methods of Dynamic Model Identification for Harbor Maneuvers using Feedforward Neural Network
• Timage -- A Robust Time Series Classification Pipeline
• Transfer Learning for Linear Regression: a Statistical Test of Gain
• Fast CRDNN: Towards on Site Training of Mobile Construction Machines
• Task Embedding Temporal Convolution Networks for Transfer Learning Problems in Renewable Power Time-Series Forecast
• Generation of Realistic Cloud Access Times for Mobile Application Testing using Transfer Learning
• An Adaptive Approach for Anomaly Detector Selection and Fine-Tuning in Time Series
• Deep Unsupervised Domain Adaptation for Time Series Classification: a Benchmark
• Diabetic Retinopathy detection by retinal image recognizing
• Handling Variable-Dimensional Time Series with Graph Neural Networks
• Learning to smell for wellness