lfads-torch: A modular and extensible implementation of latent factor analysis via dynamical systems

TL;DR

lfads-torch is an open-source, modular, and extensible Python implementation of LFADS, leveraging modern libraries to simplify neural activity denoising and facilitate research in neuroscience and engineering.

Contribution

It unifies various LFADS variants into a single, easy-to-use framework built on modern Python tools, enhancing accessibility and extendability.

Findings

State-of-the-art neural activity denoising

Simplified model configuration and training

Enhanced extensibility for research applications

Abstract

Latent factor analysis via dynamical systems (LFADS) is an RNN-based variational sequential autoencoder that achieves state-of-the-art performance in denoising high-dimensional neural activity for downstream applications in science and engineering. Recently introduced variants and extensions continue to demonstrate the applicability of the architecture to a wide variety of problems in neuroscience. Since the development of the original implementation of LFADS, new technologies have emerged that use dynamic computation graphs, minimize boilerplate code, compose model configuration files, and simplify large-scale training. Building on these modern Python libraries, we introduce lfads-torch -- a new open-source implementation of LFADS that unifies existing variants and is designed to be easier to understand, configure, and extend. Documentation, source code, and issue tracking are available at https://github.com/arsedler9/lfads-torch .