Corpus ID: 84846473

Multi-Task Time Series Analysis applied to Drug Response Modelling

@inproceedings{Bird2019MultiTaskTS,
  title={Multi-Task Time Series Analysis applied to Drug Response Modelling},
  author={Alex Bird and C. K. Williams and C. Hawthorne},
  booktitle={AISTATS},
  year={2019}
}
  • Alex Bird, C. K. Williams, C. Hawthorne
  • Published in AISTATS 2019
  • Computer Science, Mathematics
  • Time series models such as dynamical systems are frequently fitted to a cohort of data, ignoring variation between individual entities such as patients. In this paper we show how these models can be personalised to an individual level while retaining statistical power, via use of multi-task learning (MTL). To our knowledge this is a novel development of MTL which applies to time series both with and without control inputs. The modelling framework is demonstrated on a physiological drug response… CONTINUE READING
    1 Citations
    Customizing Sequence Generation with Multi-Task Dynamical Systems

    References

    SHOWING 1-10 OF 42 REFERENCES
    Multitask Gaussian Processes for Multivariate Physiological Time-Series Analysis
    • 94
    • PDF
    Input-Output Non-Linear Dynamical Systems applied to Physiological Condition Monitoring
    • 4
    • PDF
    A Framework for Individualizing Predictions of Disease Trajectories by Exploiting Multi-Resolution Structure
    • 75
    • PDF
    Nonlinear mixed-effects state space models with applications to HIV dynamics
    • 5
    Multi-task Gaussian Process Prediction
    • 735
    • PDF
    Task Clustering and Gating for Bayesian Multitask Learning
    • 539
    • PDF
    Multi-Task Learning for Classification with Dirichlet Process Priors
    • 515
    • PDF
    Personalized Risk Scoring for Critical Care Prognosis Using Mixtures of Gaussian Processes
    • 28
    • PDF
    Long Short-Term Memory
    • 32,905
    • PDF