Segmenting Hybrid Trajectories using Latent ODEs

Authors: Ruian Shi, Quaid Morris

ICML 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Here we investigate the Lat Seg ODE s ability to simultaneously perform accurate reconstruction and segmentation on synthetic and semi-synthetic data sets.
Researcher Affiliation Collaboration 1University of Toronto 2Vector Institute, Toronto 3Memorial Sloan Kettering Cancer Center.
Pseudocode Yes The full algorithm is provided in Appendix A.
Open Source Code Yes An implementation is available at: https://github. com/Ian Shi1996/Latent Segmented ODE.
Open Datasets Yes UCI Character Trajectories data set (Dua & Graff, 2017).
Dataset Splits Yes We hold out 300 validation trajectories, 150 test trajectories, and train the Lat Seg ODE base model on the SDFs contained in the remaining trajectories.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions the use of the 'ruptures library' but does not provide specific version numbers for any software dependencies.
Experiment Setup No Data parameters, model architecture and hyper-parameters are reported in Appendix E.