AI Paper Atlas

Research map / Probabilistic and scientific modeling / Dynamical systems

Shared-AE: Automatic Identification of Shared Subspaces in High-dimensional Neural and Behavioral Activity

Daiyao Yi, Hao Dong, Michael James Higley, Anne Churchland, Shreya Saxena

ICLR 2025 · Probabilistic and scientific modeling › Dynamical systems · approach: Recurrent circuit models of inference · 0 citations (OpenAlex)

Read the paper

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes Shared-AE, an autoencoder-based method that jointly learns embeddings of neural and behavioral activity to identify shared subspaces between the two modalities.

Problem

Relating neural activity to complex behavior (e.g., social interactions), where behavioral and neural features must be extracted jointly rather than from labels alone.

Approach

Learns embeddings for interconnected neural and behavioral modalities with an autoencoder architecture that automatically identifies subspaces shared across the two modalities, instead of relying on behavioral labels to define neural features.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy