Efficient hierarchical Bayesian inference for spatio-temporal regression models in neuroimaging
Authors: Ali Hashemi, Yijing Gao, Chang Cai, Sanjay Ghosh, Klaus-Robert Müller, Srikantan Nagarajan, Stefan Haufe
NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | On both synthetic and real neural data from M/EEG, we demonstrate that our methods lead to improved performance. |
| Researcher Affiliation | Academia | Ali Hashemi1,2, Yijing Gao3, Chang Cai3,4, Sanjay Ghosh3, Klaus-Robert Müller2,5,6,7, Srikantan S. Nagarajan3, and Stefan Haufe1,8,9,10 1Uncertainty, Inverse Modeling and Machine Learning Group, Technische Universität Berlin, Germany. 2Machine Learning Group, Technische Universität Berlin, Germany. 3Department of Radiology and Biomedical Imaging, University of California, San Francisco, USA. 4National Engineering Research Center for E-Learning, Central China Normal University, China. 5BIFOLD Berlin Institute for the Foundations of Learning and Data, Berlin, Germany. 6Department of Artificial Intelligence, Korea University, South Korea. 7Max Planck Institute for Informatics, Saarbrücken, Germany. 8Physikalisch-Technische Bundesanstalt, Berlin, Germany. 9Charité Universitätsmedizin Berlin, Germany. 10Bernstein Center for Computational Neuroscience, Berlin, Germany. |
| Pseudocode | No | The paper describes the algorithms through mathematical formulations and textual explanations but does not include explicit pseudocode or an algorithm block. |
| Open Source Code | Yes | The codes are publicly available at https://github.com/Ali Hashemi-ai/Dugh-Neur IPS-2021. |
| Open Datasets | No | The paper uses simulated data generated according to described procedures and real MEG/EEG data recordings, but does not provide concrete access information (URL, DOI, repository, or formal citation for public availability) for the specific datasets used in the experiments. |
| Dataset Splits | No | The paper does not provide specific details on dataset splits (e.g., training, validation, or test percentages/counts) for reproducibility. |
| Hardware Specification | Yes | All experiments are performed using Matlab on a machine with a 2.50 GHz Intel(R) Xeon(R) Platinum 8160 CPU. |
| Software Dependencies | No | The paper mentions 'Matlab' but does not specify a version number or other software dependencies with their versions. |
| Experiment Setup | Yes | In the first experiment, we compare the reconstruction performance... for a range of SNR levels, numbers of time samples, and orders of AR coefficients. ... P {1, 2, 5, 7}. ... α {0.55, 0.65, 0.7, 0.8}, which correspond to the following SNRs: SNR {1.7, 5.4, 7.4, 12} (d B). ... N0 = 3 active sources. ... T {10, 20, 50, 100}. |