Expressive dynamics models with nonlinear injective readouts enable reliable recovery of latent features from neural activity Article Swipe

MAKE IMPACT

Christopher Versteeg , Andrew R. Sedler , Jonathan McCart , Chethan Pandarinath · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2309.06402

The advent of large-scale neural recordings has enabled new methods to discover the computational mechanisms of neural circuits by understanding the rules that govern how their state evolves over time. While these \textit{neural dynamics} cannot be directly measured, they can typically be approximated by low-dimensional models in a latent space. How these models represent the mapping from latent space to neural space can affect the interpretability of the latent representation. We show that typical choices for this mapping (e.g., linear or MLP) often lack the property of injectivity, meaning that changes in latent state are not obligated to affect activity in the neural space. During training, non-injective readouts incentivize the invention of dynamics that misrepresent the underlying system and the computation it performs. Combining our injective Flow readout with prior work on interpretable latent dynamics models, we created the Ordinary Differential equations autoencoder with Injective Nonlinear readout (ODIN), which captures latent dynamical systems that are nonlinearly embedded into observed neural activity via an approximately injective nonlinear mapping. We show that ODIN can recover nonlinearly embedded systems from simulated neural activity, even when the nature of the system and embedding are unknown. Additionally, ODIN enables the unsupervised recovery of underlying dynamical features (e.g., fixed points) and embedding geometry. When applied to biological neural recordings, ODIN can reconstruct neural activity with comparable accuracy to previous state-of-the-art methods while using substantially fewer latent dimensions. Overall, ODIN's accuracy in recovering ground-truth latent features and ability to accurately reconstruct neural activity with low dimensionality make it a promising method for distilling interpretable dynamics that can help explain neural computation.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2309.06402

PDF

https://arxiv.org/pdf/2309.06402

OA Status

green

Cited By

2

Related Works

10

OpenAlex ID

https://openalex.org/W4386722175

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4386722175

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2309.06402

Digital Object Identifier

Title

Expressive dynamics models with nonlinear injective readouts enable reliable recovery of latent features from neural activity

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-09-12

Full publication date if available

Authors

Christopher Versteeg, Andrew R. Sedler, Jonathan McCart, Chethan Pandarinath

List of authors in order

Landing page

https://arxiv.org/abs/2309.06402

Publisher landing page

PDF URL

https://arxiv.org/pdf/2309.06402

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2309.06402

Direct OA link when available

Concepts

Interpretability, Embedding, Injective function, Nonlinear system, Computer science, Artificial neural network, Artificial intelligence, Representation (politics), Algorithm, Mathematics, Physics, Discrete mathematics, Law, Quantum mechanics, Political science, Politics

Top concepts (fields/topics) attached by OpenAlex

Cited by

2

Total citation count in OpenAlex

Citations by year (recent)

2025: 2

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload