Article

Improved interpretability in LFADS models using a learned, context-dependent per-trial bias

2025-10-03

Abstract excerpt

The computation-through-dynamics perspective argues that biological neural circuits process information via the continuous evolution of their internal states. Inspired by this perspective, Latent Factor Activity using Dynamical systems (LFADS, [1]) identifies a generative model consistent with the neural activity recordings. LFADS models neural dynamics with a recurrent neural network (RNN) generator, which result...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 3fecc457-4edc-5c7a-a009-ae5170683c15
DOI: 10.1101/2025.10.03.680303

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Improved interpretability in LFADS models using a learned, context-dependent per-trial biasDOI 10.1101/2025.10.03.680303Read

Preserved Embedding of Neural Population Activity for Brain Computer InterfacesSemantic proximity Read

A Generalist Intracortical Motor DecoderSemantic proximity Read

Diverse beta burst waveform motifs characterize movement-related cortical dynamicsSemantic proximity Read

Spatio-temporal transformers for decoding neural movement controlSemantic proximity Read

Closed-loop optimization of a high-dimensional generative latent space for rhythmic visual responseSemantic proximity Read

BACE: Behavior-Adaptive Connectivity Estimation for Interpretable Graphs of Neural DynamicsSemantic proximity Read

Motor cortical dynamics are shaped by multiple distinct subspaces during naturalistic behaviorSemantic proximity Read

A dynamic generative model can extract interpretable oscillatory components from multichannel neurophysiological recordingsSemantic proximity Read

Monkey-to-human transfer of brain-computer interface decodersSemantic proximity Read

Neural subspaces of imagined movements in parietal cortex remain stable over several years in humansSemantic proximity Read

Scalability of Random Forest in Myoelectric ControlSemantic proximity Read

Nonlinear manifolds underlie neural population activity during behaviourSemantic proximity Read