Contextual interference: Single task versus multi-task learning

被引:48
|
作者
Maslovat, D [1 ]
Chua, R
Lee, TD
Franks, IM
机构
[1] Univ British Columbia, Sch Human Kinet, Vancouver, BC V6T 1Z1, Canada
[2] McMaster Univ, Dept Kinesiol, Hamilton, ON L8S 4L8, Canada
关键词
contextual interference; specificity; multi-task task learning;
D O I
10.1123/mcj.8.2.213
中图分类号
Q189 [神经科学];
学科分类号
071006 ;
摘要
This experiment examined contextual interference in producing a bimanual coordination pattern of 90degrees relative phase. Acquisition, retention, and transfer performance were compared in a single-task control group and groups that performed 2 tasks in either a blocked or random presentation. Surprisingly, acquisition data revealed that both the random and control groups outperformed the blocked group. Retention data showed a typical Cl effect for performance variability, with the random group outperforming the blocked group. Neither the random nor blocked groups outperformed the control group, suggesting interference of a second task may be as beneficial to learning as extra practice on the initial task. No group effects were found during transfer performance. Results suggest that random practice is beneficial for learning only one task.
引用
收藏
页码:213 / 233
页数:21
相关论文
共 50 条
  • [1] Multi-Task Learning for Contextual Bandits
    Deshmukh, Aniket Anand
    Dogan, Urun
    Scott, Clayton
    [J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 30 (NIPS 2017), 2017, 30
  • [2] A Comparison of Multi-task Learning and Single-Task Learning Approaches
    Marquet, Thomas
    Oswald, Elisabeth
    [J]. APPLIED CRYPTOGRAPHY AND NETWORK SECURITY WORKSHOPS, ACNS 2023 SATELLITE WORKSHOPS, ADSC 2023, AIBLOCK 2023, AIHWS 2023, AIOTS 2023, CIMSS 2023, CLOUD S&P 2023, SCI 2023, SECMT 2023, SIMLA 2023, 2023, 13907 : 121 - 138
  • [3] Multi-task gradient descent for multi-task learning
    Lu Bai
    Yew-Soon Ong
    Tiantian He
    Abhishek Gupta
    [J]. Memetic Computing, 2020, 12 : 355 - 369
  • [4] Multi-task gradient descent for multi-task learning
    Bai, Lu
    Ong, Yew-Soon
    He, Tiantian
    Gupta, Abhishek
    [J]. MEMETIC COMPUTING, 2020, 12 (04) : 355 - 369
  • [5] Contextual Skill Proficiency via Multi-task Learning at LinkedIn
    Yan, Xiao
    Ma, Ada
    Yang, Jaewon
    Zhu, Lin
    Jing, How
    Bollinger, Jacob
    He, Qi
    [J]. PROCEEDINGS OF THE 30TH ACM INTERNATIONAL CONFERENCE ON INFORMATION & KNOWLEDGE MANAGEMENT, CIKM 2021, 2021, : 4273 - 4282
  • [6] Learning Sparse Task Relations in Multi-Task Learning
    Zhang, Yu
    Yang, Qiang
    [J]. THIRTY-FIRST AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2017, : 2914 - 2920
  • [7] Task Variance Regularized Multi-Task Learning
    Mao, Yuren
    Wang, Zekai
    Liu, Weiwei
    Lin, Xuemin
    Hu, Wenbin
    [J]. IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2023, 35 (08) : 8615 - 8629
  • [8] Task Switching Network for Multi-task Learning
    Sun, Guolei
    Probst, Thomas
    Paudel, Danda Pani
    Popovic, Nikola
    Kanakis, Menelaos
    Patel, Jagruti
    Dai, Dengxin
    Van Gool, Luc
    [J]. 2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021), 2021, : 8271 - 8280
  • [9] Systematically increasing contextual interference is beneficial for learning single task
    Feghhi, Iman
    Valizade, Roholla
    [J]. 2ND WORLD CONFERENCE ON PSYCHOLOGY, COUNSELLING AND GUIDANCE-2011, 2011, 30
  • [10] Learning Multi-Level Task Groups in Multi-Task Learning
    Han, Lei
    Zhang, Yu
    [J]. PROCEEDINGS OF THE TWENTY-NINTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2015, : 2638 - 2644