Timezone: »

Targeted Neural Dynamical Modeling
Cole Hurwitz · Akash Srivastava · Kai Xu · Justin Jude · Matthew Perich · Lee Miller · Matthias Hennig

Tue Dec 07 08:30 AM -- 10:00 AM (PST) @ None #None

Latent dynamics models have emerged as powerful tools for modeling and interpreting neural population activity. Recently, there has been a focus on incorporating simultaneously measured behaviour into these models to further disentangle sources of neural variability in their latent space. These approaches, however, are limited in their ability to capture the underlying neural dynamics (e.g. linear) and in their ability to relate the learned dynamics back to the observed behaviour (e.g. no time lag). To this end, we introduce Targeted Neural Dynamical Modeling (TNDM), a nonlinear state-space model that jointly models the neural activity and external behavioural variables. TNDM decomposes neural dynamics into behaviourally relevant and behaviourally irrelevant dynamics; the relevant dynamics are used to reconstruct the behaviour through a flexible linear decoder and both sets of dynamics are used to reconstruct the neural activity through a linear decoder with no time lag. We implement TNDM as a sequential variational autoencoder and validate it on simulated recordings and recordings taken from the premotor and motor cortex of a monkey performing a center-out reaching task. We show that TNDM is able to learn low-dimensional latent dynamics that are highly predictive of behaviour without sacrificing its fit to the neural data.

Author Information

Cole Hurwitz (University of Edinburgh)
Akash Srivastava (MIT–IBM Watson AI Lab)
Kai Xu (University of Edinburgh)
Justin Jude (University of Edinburgh)
Matthew Perich (Icahn School of Medicine at Mount Sinai)
Lee Miller (Northwestern University at Chicago)
Matthias Hennig (University of Edinburgh)

More from the Same Authors