More Like this

1. CREIMBO: Cross-Regional Ensemble Interactions in Multi-view Brain Observations

   Mudrik, Noga; Ly, Ryan; Ruebel, Oliver; Charles, Adam S (January 2025, The International Conference on Learning Representations)

   Modern recordings of neural activity provide diverse observations of neurons across brain areas, behavioral conditions, and subjects; presenting an exciting opportunity to reveal the fundamentals of brain-wide dynamics. Current analysis methods, however, often fail to fully harness the richness of such data, as they provide either uninterpretable representations (e.g., via deep networks) or oversimplify models (e.g., by assuming stationary dynamics or analyzing each session independently). Here, instead of regarding asynchronous neural recordings that lack alignment in neural identity or brain areas as a limitation, we leverage these diverse views into the brain to learn a unified model of neural dynamics. Specifically, we assume that brain activity is driven by multiple hidden global sub-circuits. These sub-circuits represent global basis interactions between neural ensembles—functional groups of neurons—such that the time-varying decomposition of these sub-circuits defines how the ensembles’ interactions evolve over time non-stationarily and non-linearly. We discover the neural ensembles underlying non-simultaneous observations, along with their non-stationary evolving interactions, with our new model, CREIMBO (Cross-Regional Ensemble Interactions in Multi-view Brain Observations). CREIMBO identifies the hidden composition of per-session neural ensembles through novel graph-driven dictionary learning and models the ensemble dynamics on a low-dimensional manifold spanned by a sparse time-varying composition of the global sub-circuits. Thus, CREIMBO disentangles overlapping temporal neural processes while preserving interpretability due to the use of a shared underlying sub-circuit basis. Moreover, CREIMBO distinguishes session-specific computations from global (session-invariant) ones by identifying session covariates and variations in sub-circuit activations. We demonstrate CREIMBO’s ability to recover true components in synthetic data, and uncover meaningful brain dynamics in human high-density electrode recordings, including cross-subject neural mechanisms as well as inter- vs. intra-region dynamical motifs. Furthermore, using mouse whole-brain recordings, we show CREIMBO’s ability to discover dynamical interactions that capture task and behavioral variables and meaningfully align with the biological importance of the brain areas they represent 

   more » « less
2. Adversarial Domain Adaptation for Stable Brain-Machine Interfaces

   Farshchian, A; Gallego, JA; Cohen, JP; Bengio, Y; Miller, LE; Solla, SA (January 2019, International Conference on Learning Representations)

   Brain-Machine Interfaces (BMIs) have recently emerged as a clinically viable option to restore voluntary movements after paralysis. These devices are based on the ability to extract information about movement intent from neural signals recorded using multi-electrode arrays chronically implanted in the motor cortices of the brain. However, the inherent loss and turnover of recorded neurons requires repeated recalibrations of the interface, which can potentially alter the day-to-day user experience. The resulting need for continued user adaptation interferes with the natural, subconscious use of the BMI. Here, we introduce a new computational approach that decodes movement intent from a low-dimensional latent representation of the neural data. We implement various domain adaptation methods to stabilize the interface over significantly long times. This includes Canonical Correlation Analysis used to align the latent variables across days; this method requires prior point-to-point correspondence of the time series across domains. Alternatively, we match the empirical probability distributions of the latent variables across days through the minimization of their Kullback-Leibler divergence. These two methods provide a significant and comparable improvement in the performance of the interface. However, implementation of an Adversarial Domain Adaptation Network trained to match the empirical probability distribution of the residuals of the reconstructed neural signals outperforms the two methods based on latent variables, while requiring remarkably few data points to solve the domain adaptation problem. 

   more » « less
3. Prioritized learning of cross-population neural dynamics

   https://doi.org/10.1088/1741-2552/ade569  

   Jha, Trisha; Sani, Omid_G; Pesaran, Bijan; Shanechi, Maryam_M (June 2025, Journal of Neural Engineering)

   Abstract Objective. Improvements in recording technology for multi-region simultaneous recordings enable the study of interactions among distinct brain regions. However, a major computational challenge in studying cross-regional, or cross-population dynamics in general, is that the cross-population dynamics can be confounded or masked by within-population dynamics. Approach. Here, we propose cross-population prioritized linear dynamical modeling (CroP-LDM) to tackle this challenge. CroP-LDM learns the cross-population dynamics in terms of a set of latent states using a prioritized learning approach, such that they are not confounded by within-population dynamics. Further, CroP-LDM can infer the latent states both causally in time using only past neural activity and non-causally in time, unlike some prior dynamic methods whose inference is non-causal. Results. First, through comparisons with various LDM methods, we show that the prioritized learning objective in CroP-LDM is key for accurate learning of cross-population dynamics. Second, using multi-regional bilateral motor and premotor cortical recording during a naturalistic movement task, we demonstrate that CroP-LDM better learns cross-population dynamics compared to recent static and dynamic methods, even when using a low dimensionality. Finally, we demonstrate how CroP-LDM can quantify dominant interaction pathways across brain regions in an interpretable manner. Significance. Overall, these results show that our approach can be a useful framework for addressing challenges associated with modeling dynamics across brain regions. 

   more » « less
4. Calibrating Bayesian decoders of neural spiking activity

   https://doi.org/10.1523/JNEUROSCI.2158-23.2024  

   Wei, Ganchao; Tajik_Mansouri, Zeinab; Wang, Xiaojing; Stevenson, Ian H (March 2024, The Journal of Neuroscience)

   Accurately decoding external variables from observations of neural activity is a major challenge in systems neuroscience. Bayesian decoders, that provide probabilistic estimates, are some of the most widely used. Here we show how, in many common settings, the probabilistic predictions made by traditional Bayesian decoders are overconfident. That is, the estimates for the decoded stimulus or movement variables are more certain than they should be. We then show how Bayesian decoding with latent variables, taking account of low-dimensional shared variability in the observations, can improve calibration, although additional correction for overconfidence is still needed. Using data from males, we examine: 1) decoding the direction of grating stimuli from spike recordings in primary visual cortex in monkeys, 2) decoding movement direction from recordings in primary motor cortex in monkeys, 3) decoding natural images from multi-region recordings in mice, and 4) decoding position from hippocampal recordings in rats. For each setting we characterize the overconfidence, and we describe a possible method to correct miscalibration post-hoc. Properly calibrated Bayesian decoders may alter theoretical results on probabilistic population coding and lead to brain machine interfaces that more accurately reflect confidence levels when identifying external variables. Significance Statement Bayesian decoding is a statistical technique for making probabilistic predictions about external stimuli or movements based on recordings of neural activity. These predictions may be useful for robust brain machine interfaces or for understanding perceptual or behavioral confidence. However, the probabilities produced by these models do not always match the observed outcomes. Just as a weather forecast predicting a 50% chance of rain may not accurately correspond to an outcome of rain 50% of the time, Bayesian decoders of neural activity can be miscalibrated as well. Here we identify and measure miscalibration of Bayesian decoders for neural spiking activity in a range of experimental settings. We compare multiple statistical models and demonstrate how overconfidence can be corrected. 

   more » « less
5. Deep inference of latent dynamics with spatio-temporal super resolution using selective backpropagation through time

   Zhu, F; Sedler, AR; Grier, HA; Ahad, N; Davenport, MA; Kaufman, MT; Giovannucci, A; Pandarinath, C (January 2021, Advances in Neural Information Processing Systems (NeurIPS))

   Modern neural interfaces allow access to the activity of up to a million neurons within brain circuits. However, bandwidth limits often create a trade-off between greater spatial sampling (more channels or pixels) and the temporal frequency of sampling. Here we demonstrate that it is possible to obtain spatio-temporal super-resolution in neuronal time series by exploiting relationships among neurons, embedded in latent low-dimensional population dynamics. Our novel neural network training strategy, selective backpropagation through time (SBTT), enables learning of deep generative models of latent dynamics from data in which the set of observed variables changes at each time step. The resulting models are able to infer activity for missing samples by combining observations with learned latent dynamics. We test SBTT applied to sequential autoencoders and demonstrate more efficient and higher-fidelity characterization of neural population dynamics in electrophysiological and calcium imaging data. In electrophysiology, SBTT enables accurate inference of neuronal population dynamics with lower interface bandwidths, providing an avenue to significant power savings for implanted neuroelectronic interfaces. In applications to two-photon calcium imaging, SBTT accurately uncovers high-frequency temporal structure underlying neural population activity, substantially outperforming the current state-of-the-art. Finally, we demonstrate that performance could be further improved by using limited, high-bandwidth sampling to pretrain dynamics models, and then using SBTT to adapt these models for sparsely-sampled data. 

   more » « less