PT - JOURNAL ARTICLE AU - Kim, Timothy Doyeon AU - Luo, Thomas Zhihao AU - Can, Tankut AU - Krishnamurthy, Kamesh AU - Pillow, Jonathan W. AU - Brody, Carlos D. TI - Flow-field inference from neural data using deep recurrent networks AID - 10.1101/2023.11.14.567136 DP - 2023 Jan 01 TA - bioRxiv PG - 2023.11.14.567136 4099 - http://biorxiv.org/content/early/2023/11/16/2023.11.14.567136.short 4100 - http://biorxiv.org/content/early/2023/11/16/2023.11.14.567136.full AB - Computations involved in processes such as decision-making, working memory, and motor control are thought to emerge from the dynamics governing the collective activity of neurons in large populations. But the estimation of these dynamics remains a significant challenge. Here we introduce Flow-field Inference from Neural Data using deep Recurrent networks (FINDR), an unsupervised deep learning method that can infer low-dimensional nonlinear stochastic dynamics underlying neural population activity. Using population spike train data from frontal brain regions of rats performing an auditory decision-making task, we demonstrate that FINDR outperforms existing methods in capturing the heterogeneous responses of individual neurons. We further show that FINDR can discover interpretable low-dimensional dynamics when it is trained to disentangle task-relevant and irrelevant components of the neural population activity. Importantly, the low-dimensional nature of the learned dynamics allows for explicit visualization of flow fields and attractor structures. We suggest FINDR as a powerful method for revealing the low-dimensional task-relevant dynamics of neural populations and their associated computations.Competing Interest StatementThe authors have declared no competing interest.