Mcfly: Automated deep learning on time series

Abstract Deep learning is receiving increasing attention in the scientific community, but for researchers with no or limited machine learning experience it can be difficult to get started. In particular, the so-called hyperparameter selection, which is critical to successfully train a model, requires a good understanding of deep learning and some experience training models. We present mcfly, a Python package for deep learning for time series classification, designed to ease training by providing automated hyperparameter selection. We evaluated mcfly by organizing two workshops.

[1]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Yoshua Bengio,et al.  Learning deep physiological models of affect , 2013, IEEE Computational Intelligence Magazine.

[3]  Younghoon Kim,et al.  Classification of Heart Diseases Based On ECG Signals Using Long Short-Term Memory , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[4]  Timon B. Heinis,et al.  Improving Usage Metrics for Pay-per-Use Pricing with IoT Technology and Machine Learning , 2018, Research-Technology Management.

[5]  Sergio Escalera,et al.  Analysis of the AutoML Challenge Series 2015-2018 , 2019, Automated Machine Learning.

[6]  Doo Seop Eom,et al.  Smartphone-Based Traveled Distance Estimation Using Individual Walking Patterns for Indoor Localization , 2018, Sensors.

[7]  Jungjoon Kim,et al.  Wave2Vec: Vectorizing Electroencephalography Bio-Signal for Prediction of Brain Disease , 2018, International journal of environmental research and public health.

[8]  Alexander J. Casson,et al.  Human activity recognition from inertial sensor time-series using batch normalized deep LSTM recurrent networks , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[9]  Geoffrey I. Webb,et al.  InceptionTime: Finding AlexNet for Time Series Classification , 2020, Data Min. Knowl. Discov..

[10]  Sridha Sridharan,et al.  Deep Classification of Epileptic Signals , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[11]  Randal S. Olson,et al.  Automating Biomedical Data Science Through Tree-Based Pipeline Optimization , 2016, EvoApplications.

[12]  Daniel Roggen,et al.  Deep Convolutional and LSTM Recurrent Neural Networks for Multimodal Wearable Activity Recognition , 2016, Sensors.

[13]  Didier Stricker,et al.  Creating and benchmarking a new dataset for physical activity monitoring , 2012, PETRA '12.

[14]  Yongwha Chung,et al.  Resource-Efficient Pet Dog Sound Events Classification Using LSTM-FCN Based on Time-Series Data , 2018, Sensors.

[15]  Qingquan Song,et al.  Auto-Keras: Efficient Neural Architecture Search with Network Morphism , 2018 .

[16]  Aaron Klein,et al.  Efficient and Robust Automated Machine Learning , 2015, NIPS.

[17]  Peng Wang,et al.  A Time-Distributed Spatiotemporal Feature Learning Method for Machine Health Monitoring with Multi-Sensor Time Series , 2018, Sensors.

[18]  Lars Kotthoff,et al.  Auto-WEKA 2.0: Automatic model selection and hyperparameter optimization in WEKA , 2017, J. Mach. Learn. Res..

[19]  Shie Mannor,et al.  The cross entropy method for classification , 2005, ICML.

[20]  Germain Forestier,et al.  Deep learning for time series classification: a review , 2018, Data Mining and Knowledge Discovery.

[21]  Klaus-Robert Müller,et al.  Efficient BackProp , 2012, Neural Networks: Tricks of the Trade.

[22]  Didier Stricker,et al.  Introducing a New Benchmarked Dataset for Activity Monitoring , 2012, 2012 16th International Symposium on Wearable Computers.

[23]  David H. Wolpert,et al.  The Lack of A Priori Distinctions Between Learning Algorithms , 1996, Neural Computation.

[24]  A. Ng.  Feature selection, L1 vs. L2 regularization, and rotational invariance , 2004, Twenty-first international conference on Machine learning - ICML '04.

[25]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[26]  Franz J. Király,et al.  sktime: A Unified Interface for Machine Learning with Time Series , 2019, ArXiv.

[27]  Patrycja Kowalek,et al.  Classification of diffusion modes in single-particle tracking data: Feature-based versus deep-learning approach. , 2019, Physical review. E.