Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles
This work addresses the challenge of accurately modeling mixed neural populations in systems neuroscience, offering incremental improvements to existing neural latent variable models.
The paper tackled the problem of modeling neural population activity by introducing feature sharing across tuning curves and soft clustering for ensemble detection, which improved performance and interpretability on complex latent manifolds, including recovering distinct ensembles and inferring toroidal latents in a grid cell dataset.
Systems neuroscience relies on two complementary views of neural data, characterized by single neuron tuning curves and analysis of population activity. These two perspectives combine elegantly in neural latent variable models that constrain the relationship between latent variables and neural activity, modeled by simple tuning curve functions. This has recently been demonstrated using Gaussian processes, with applications to realistic and topologically relevant latent manifolds. Those and previous models, however, missed crucial shared coding properties of neural populations. We propose feature sharing across neural tuning curves which significantly improves performance and helps optimization. We also propose a solution to the ensemble detection problem, where different groups of neurons, i.e., ensembles, can be modulated by different latent manifolds. Achieved through a soft clustering of neurons during training, this allows for the separation of mixed neural populations in an unsupervised manner. These innovations lead to more interpretable models of neural population activity that train well and perform better even on mixtures of complex latent manifolds. Finally, we apply our method on a recently published grid cell dataset, and recover distinct ensembles, infer toroidal latents and predict neural tuning curves in a single integrated modeling framework.