Event Classification with Multi-step Machine Learning

The usefulness and value of Multi-step Machine Learning (ML), where a task is organized into connected sub-tasks with known intermediate inference goals, as opposed to a single large model learned end-to-end without intermediate sub-tasks, is presented. Pre-optimized ML models are connected and better performance is obtained by re-optimizing the connected one. The selection of an ML model from several small ML model candidates for each sub-task has been performed by using the idea based on Neural Architecture Search (NAS). In this paper, Differentiable Architecture Search (DARTS) and Single Path One-Shot NAS (SPOS-NAS) are tested, where the construction of loss functions is improved to keep all ML models smoothly learning. Using DARTS and SPOS-NAS as an optimization and selection as well as the connections for multi-step machine learning systems, we find that (1) such a system can quickly and successfully select highly performant model combinations, and (2) the selected models are consistent with baseline algorithms, such as grid search, and their outputs are well controlled.

[1]  Qi Tian,et al.  Progressive Differentiable Architecture Search: Bridging the Depth Gap Between Search and Evaluation , 2019, 2019 IEEE/CVF International Conference on Computer Vision (ICCV).

[2]  장윤희,et al.  Y. , 2003, Industrial and Labor Relations Terms.

[3]  P. Alam.  ‘S’ , 2021, Composites Engineering: An A–Z Guide.

[4]  Vladlen Koltun,et al.  Multi-Task Learning as Multi-Objective Optimization , 2018, NeurIPS.

[5]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[6]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Andrew J. Davison,et al.  End-To-End Multi-Task Learning With Attention , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Xiangyu Zhang,et al.  Single Path One-Shot Neural Architecture Search with Uniform Sampling , 2019, ECCV.

[9]  Li Fei-Fei,et al.  Dynamic Task Prioritization for Multitask Learning , 2018, ECCV.

[10]  Quoc V. Le,et al.  Efficient Neural Architecture Search via Parameter Sharing , 2018, ICML.

[11]  Yutaro Iiyama,et al.  An Improvement of Object Detection Performance using Multi-step Machine Learnings , 2021, ArXiv.

[12]  Alok Aggarwal,et al.  Regularized Evolution for Image Classifier Architecture Search , 2018, AAAI.

[13]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[14]  Danna Zhou,et al.  d. , 1840, Microbial pathogenesis.

[15]  Qingfu Zhang,et al.  Pareto Multi-Task Learning , 2019, NeurIPS.

[16]  이현주.  Q. , 2005 .

[17]  P. Alam.  ‘L’ , 2021, Composites Engineering: An A–Z Guide.

[18]  Roberto Cipolla,et al.  Multi-task Learning Using Uncertainty to Weigh Losses for Scene Geometry and Semantics , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[19]  Thomas de Quincey.  [C] , 2000, The Works of Thomas De Quincey, Vol. 1: Writings, 1799–1820.

[20]  Zhao Chen,et al.  GradNorm: Gradient Normalization for Adaptive Loss Balancing in Deep Multitask Networks , 2017, ICML.

[21]  Jian Sun,et al.  DetNAS: Backbone Search for Object Detection , 2019, NeurIPS.

[22]  Theodore Lim,et al.  SMASH: One-Shot Model Architecture Search through HyperNetworks , 2017, ICLR.

[23]  M. Berz,et al.  Nuclear Instruments and Methods in Physics Research, Section A: Accelerators, Spectrometers, Detectors and Associated Equipment: Editorial , 2006 .

[24]  Quoc V. Le,et al.  Understanding and Simplifying One-Shot Architecture Search , 2018, ICML.

[25]  이화영.  X , 1960, Chinese Plants Names Index 2000-2009.

[26]  P. Alam.  ‘K’ , 2021, Composites Engineering.

[27]  P. Alam.  ‘N’ , 2021, Composites Engineering: An A–Z Guide.