Additionally,bGPFA uses automatic relevance determination to infer the dimensionality of neural activity directly from the training data during optimization.

In this work, we introduce LangevinFlow, a sequential Varia-tional Auto-Encoder where the time evolution of latent variables is governed by the underdamped Langevin equation. Our approach incorporates physical priors -- such as inertia, damping, a learned potential function, and stochastic forces -- to represent both autonomous and non-autonomous processes in neural systems. Crucially, the potential function is parameterized as a network of locally coupled oscillators, biasing the model toward oscillatory and flow-like behaviors observed in biological neural populations. Our model features a recurrent encoder, a one-layer Transformer decoder, and Langevin dynamics in the latent space. Empirically, our method outperforms state-of-the-art baselines on synthetic neural populations generated by a Lorenz attractor, closely matching ground-truth firing rates. On the Neural Latents Benchmark (NLB), the model achieves superior held-out neuron likelihoods (bits per spike) and forward prediction accuracy across four challenging datasets. It also matches or surpasses alternative methods in decoding behavioral metrics such as hand velocity. Overall, this work introduces a flexible, physics-inspired, high-performing framework for modeling complex neural population dynamics and their unobserved influences.

Understanding the neural implementation of complex human behaviors is one of the major goals in neuroscience. To this end, it is crucial to find a true representation of the neural data, which is challenging due to the high complexity of behaviors and the low signal-to-ratio (SNR) of the signals. Here, we propose a novel unsupervised learning framework, Neural Latent Aligner (NLA), to find well-constrained, behaviorally relevant neural representations of complex behaviors. The key idea is to align representations across repeated trials to learn cross-trial consistent information. Furthermore, we propose a novel, fully differentiable time warping model (TWM) to resolve the temporal misalignment of trials. When applied to intracranial electrocorticography (ECoG) of natural speaking, our model learns better representations for decoding behaviors than the baseline models, especially in lower dimensional space. The TWM is empirically validated by measuring behavioral coherence between aligned trials. The proposed framework learns more cross-trial consistent representations than the baselines, and when visualized, the manifold reveals shared neural trajectories across trials.

The NIH has awarded High-Risk, High-Reward grants to three Emory University researchers pursuing highly innovative research that has the potential for broad impact. The program this year awarded a total of 106 grants totaling approximately $329 million over five years to support research proposals that, due to their inherent risk, may struggle in the traditional peer review process despite their transformative potential. The National Institutes of Health (NIH) is awarding Chethan Pandarinath the 2021 Director's New Innovator Award, an honor that recognizes exceptionally creative early career investigators. Pandarinath, an assistant professor in the Wallace H. Coulter Department of Biomedical Engineering (Coulter BME), is using artificial intelligence to build brain-machine interfaces to assist people with paralysis, specifically those with Amyotrophic Lateral Sclerosis (ALS). Part of the NIH's High-Risk, High-Reward Research program, Pandarinath's $2.4 million award grant will support his team's launch of a clinical trial this fall, implanting sensors into the brains of paralyzed people with ALS.

Artificial intelligence and neuroscience have a very close relationship. Knowledge from neuroscience can be utilized for improving AI and it is also true in reverse. As we have known, the artificial neural network gets its idea from the way our brain works and so do many approaches. This makes sense because if we want to build a thing on the basis of another thing, why not conduct an investigation into the original one. In opposite, AI can also support works related to neuroscience.

Chethan Pandarinath wants to enable people with paralysed limbs to reach out and grasp with a robotic arm as naturally as they would their own. To help him meet this goal, he has collected recordings of brain activity in people with paralysis. His hope, which is shared by many other researchers, is that he will be able to identify the patterns of electrical activity in neurons that correspond to a person's attempts to move their arm in a particular way, so that the instruction can then be fed to a prosthesis. Essentially, he wants to read their minds. "It turns out, that's a really challenging problem," says Pandarinath, a biomedical engineer at the Georgia Institute of Technology in Atlanta. "These signals from the brain -- they're really complicated."