Gosztolai Adam, Peach Robert L, Arnaudon Alexis, Barahona Mauricio, Vandergheynst Pierre
Institute of Artificial Intelligence, Medical University of Vienna, Vienna, Austria.
Department of Neurology, University Hospital Würzburg, Würzburg, Germany.
Nat Methods. 2025 Mar;22(3):612-620. doi: 10.1038/s41592-024-02582-2. Epub 2025 Feb 17.
The dynamics of neuron populations commonly evolve on low-dimensional manifolds. Thus, we need methods that learn the dynamical processes over neural manifolds to infer interpretable and consistent latent representations. We introduce a representation learning method, MARBLE, which decomposes on-manifold dynamics into local flow fields and maps them into a common latent space using unsupervised geometric deep learning. In simulated nonlinear dynamical systems, recurrent neural networks and experimental single-neuron recordings from primates and rodents, we discover emergent low-dimensional latent representations that parametrize high-dimensional neural dynamics during gain modulation, decision-making and changes in the internal state. These representations are consistent across neural networks and animals, enabling the robust comparison of cognitive computations. Extensive benchmarking demonstrates state-of-the-art within- and across-animal decoding accuracy of MARBLE compared to current representation learning approaches, with minimal user input. Our results suggest that a manifold structure provides a powerful inductive bias to develop decoding algorithms and assimilate data across experiments.
神经元群体的动力学通常在低维流形上演变。因此，我们需要能够在神经流形上学习动力学过程的方法，以推断出可解释且一致的潜在表示。我们引入了一种表示学习方法MARBLE，它将流形上的动力学分解为局部流场，并使用无监督几何深度学习将其映射到一个共同的潜在空间。在模拟非线性动力系统、循环神经网络以及来自灵长类动物和啮齿动物的实验单神经元记录中，我们发现了新兴的低维潜在表示，这些表示在增益调制、决策和内部状态变化期间为高维神经动力学设定参数。这些表示在神经网络和动物之间是一致的，从而能够对认知计算进行稳健比较。广泛的基准测试表明，与当前的表示学习方法相比，MARBLE在动物内部和跨动物解码准确性方面达到了最先进水平，且用户输入最少。我们的结果表明，流形结构为开发解码算法和整合跨实验数据提供了强大的归纳偏差。
