Abstract
Extracting causal connections can advance interpretable AI and machine learning. Granger causality (GC) is a robust statistical method for estimating directed influences (DC) between signals. While GC has been widely applied to analysing neuronal signals in biological neural networks and other domains, its application to complex, nonlinear, and multistable neural networks is less explored. In this study, we applied time-domain multivariate Granger causality (MVGC) to the time series neural activity of all nodes in a trained multistable biologically based decision neural network model with real-time decision uncertainty monitoring. Our analysis demonstrated that challenging two-choice decisions, where input signals could be closely matched, and the appropriate application of fine-grained sliding time windows, could readily reveal the original model’s DC. Furthermore, the identified DC varied based on whether the network had correct or error decisions. Integrating the identified DC from different decision outcomes recovered most of the original model’s architecture, despite some spurious and missing connectivity. This approach could be used as an initial exploration to enhance the interpretability and transparency of dynamic multistable and nonlinear biological or AI systems by revealing causal connections throughout different phases of neural network dynamics and outcomes.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015). https://doi.org/10.1038/nature14539
Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning http://arxiv.org/abs/1702.08608 (2017). https://doi.org/10.48550/arXiv.1702.08608
Hassija, V., et al.: Interpreting black-box models: a review on explainable artificial intelligence. Cogn. Comput. 16, 45–74 (2024). https://doi.org/10.1007/s12559-023-10179-8
Samek, W., Wiegand, T., Müller, K.-R.: Explainable artificial intelligence: understanding, visualizing and interpreting deep learning models. http://arxiv.org/abs/1708.08296 (2017). https://doi.org/10.48550/arXiv.1708.08296
Breakspear, M.: Dynamic models of large-scale brain activity. Nat. Neurosci. 20, 340–352 (2017). https://doi.org/10.1038/nn.4497
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015). https://doi.org/10.1038/nature14236
Barnett, L., Seth, A.K.: The MVGC multivariate Granger causality toolbox: a new approach to Granger-causal inference. J. Neurosci. Methods 223, 50–68 (2014). https://doi.org/10.1016/j.jneumeth.2013.10.018
Bressler, S.L., Seth, A.K.: Wiener-Granger Causality: a well established methodology. Neuroimage 58, 323–329 (2011). https://doi.org/10.1016/j.neuroimage.2010.02.059
Yuan, T., Qin, S.J.: Root cause diagnosis of plant-wide oscillations using Granger causality. J. Process Control 24, 450–459 (2014). https://doi.org/10.1016/j.jprocont.2013.11.009
Guo, S., Seth, A.K., Kendrick, K.M., Zhou, C., Feng, J.: Partial Granger causality—eliminating exogenous inputs and latent variables. J. Neurosci. Methods 172, 79–93 (2008). https://doi.org/10.1016/j.jneumeth.2008.04.011
Atiya, N.A.A., Rañó, I., Prasad, G., Wong-Lin, K.: A neural circuit model of decision uncertainty and change-of-mind. Nat. Commun. 10, 2287 (2019). https://doi.org/10.1038/s41467-019-10316-8
Wong, K.-F., Wang, X.-J.: A recurrent network mechanism of time integration in perceptual decisions. J. Neurosci. 26, 1314–1328 (2006). https://doi.org/10.1523/JNEUROSCI.3733-05.2006
Lin, X., Zou, X., Ji, Z., Huang, T., Wu, S., Mi, Y.: A brain-inspired computational model for spatio-temporal information processing. Neural Netw. 143, 74–87 (2021). https://doi.org/10.1016/j.neunet.2021.05.015
Ding, M., Bressler, S.L., Yang, W., Liang, H.: Short-window spectral analysis of cortical event-related potentials by adaptive multivariate autoregressive modeling: data preprocessing, model validation, and variability assessment. Biol. Cybern. 83, 35–45 (2000). https://doi.org/10.1007/s004229900137
Benjamini, Y., Yekutieli, D.: The control of the false discovery rate in multiple testing under dependency. Ann. Stat. 29, 1165–1188 (2001). https://doi.org/10.1214/aos/1013699998
Roitman, J.D., Shadlen, M.N.: Response of neurons in the lateral intraparietal area during a combined visual discrimination reaction time task. J. Neurosci. 22, 9475–9489 (2002). https://doi.org/10.1523/JNEUROSCI.22-21-09475.2002
Cekic, S., Grandjean, D., Renaud, O.: Time, frequency, and time-varying Granger-causality measures in neuroscience. Stat. Med. 37, 1910–1931 (2018). https://doi.org/10.1002/sim.7621
Han, Y., Huang, G., Song, S., Yang, L., Wang, H., Wang, Y.: Dynamic neural networks: a survey. IEEE Trans. Pattern Anal. Mach. Intell. 44, 7436–7456 (2022). https://doi.org/10.1109/TPAMI.2021.3117837
Venzke, A., Chatzivasileiadis, S.: Verification of neural network behaviour: formal guarantees for power system applications. IEEE Trans. Smart Grid. 12, 383–397 (2021). https://doi.org/10.1109/TSG.2020.3009401
Wang, L., Zhang, L., Wang, J., Yi, Z.: Memory mechanisms for discriminative visual tracking algorithms with deep neural networks. IEEE Trans. Cogn. Develop. Syst. 12, 98–108 (2020). https://doi.org/10.1109/TCDS.2019.2900506
Barrett, A.B., Barnett, L., Seth, A.K.: Multivariate Granger causality and generalized variance. Phys. Rev. E 81, 041907 (2010). https://doi.org/10.1103/PhysRevE.81.041907
Youssofzadeh, V., Prasad, G., Naeem, M., Wong-Lin, K.: Temporal information of directed causal connectivity in multi-trial ERP data using partial granger causality. Neuroinformatics 14, 99–120 (2016). https://doi.org/10.1007/s12021-015-9281-6
Acknowledgement
A.A. and K.W.-L. were supported by HSC R&D (STL/5540/19) and MRC (MC_OC_20020). We are grateful for access to the Tier 2 High-Performance Computing resources provided by the Northern Ireland High-Performance Computing (NI-HPC) facility funded by the UK Engineering and Physical Sciences Research Council (EPSRC), Grant No. EP/T022175/1.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Asadpour, A., Wong-Lin, K. (2024). Can Multivariate Granger Causality Detect Directed Connectivity of a Multistable and Dynamic Biological Decision Network Model?. In: Zheng, H., Glass, D., Mulvenna, M., Liu, J., Wang, H. (eds) Advances in Computational Intelligence Systems. UKCI 2024. Advances in Intelligent Systems and Computing, vol 1462. Springer, Cham. https://doi.org/10.1007/978-3-031-78857-4_14
Download citation
DOI: https://doi.org/10.1007/978-3-031-78857-4_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-78856-7
Online ISBN: 978-3-031-78857-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)