lfads-torch: A modular and extensible implementation of latent factor analysis via dynamical systems
This work provides a more accessible and configurable tool for researchers in neuroscience and related fields, but it is incremental as it focuses on improving the implementation rather than advancing the core method.
The paper introduces lfads-torch, a modular and extensible implementation of latent factor analysis via dynamical systems (LFADS), which is an RNN-based variational sequential autoencoder for denoising high-dimensional neural activity, achieving state-of-the-art performance in science and engineering applications.
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 .