The purpose of this resource is a computational framework of a machine learning technique to analyze multi-region electrophysiological recordings and learn electrical connectome networks that are related to outcomes of interest (e.g., mouse model of depression). The learned networks are visualizable and explainable.
Talbot, A., Dunson, D., Dzirasa, K., & Carlson, D. (2020). Supervised Autoencoders Learn Robust Joint Factor Models of Neural Activity. arXiv preprint arXiv:2004.05209.
Gallagher, N., Ulrich, K. R., Talbot, A., Dzirasa, K., Carin, L., & Carlson, D. E. (2017). Cross-spectral factor analysis. In Advances in Neural Information Processing Systems (pp. 6842-6852).
Hultman, R., Ulrich, K., Sachs, B. D., Blount, C., Carlson, D. E., Ndubuizu, N., ... & Dzirasa, K. (2018). Brain-wide electrical spatiotemporal dynamics encode depression vulnerability. Cell, 173(1), 166-180.