Research map / Probabilistic and scientific modeling / Dynamical systems
Probabilistic Tensor Decomposition of Neural Population Spiking Activity
Hugo Soulat, Sepiedeh Keshavarzi, Troy William Margrie, Maneesh Sahani
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use VB-GCP instead of CP and Poisson GCP | tensor decomposition of mouse RSP spike data · RSP multisensory spike recordings, held-out trials | variance explained | Improved |
| use VB-GCP instead of CP and Poisson GCP | tensor decomposition of mouse RSP spike data · RSP multisensory spike recordings, held-out trials | Poisson deviance explained | Improved |
| use VB-GCP instead of CP and GCP | tensor decomposition · RSP spike data, cross-validation folds | similarity of factors across folds | Improved |
| increase tensor rank R | VB-GCP · RSP spike data, held-out | test variance and deviance explained | Improved |
| increase tensor rank R | CP and GCP (maximum likelihood) · RSP spike data, held-out | test variance and deviance explained | Hurt |
| remove automatic relevance determination (ARD) priors (ablation) | VB-GCP · simulation 1, R=6 initialisation, true R=4 | rank recovery | Hurt |
| use ARD-based rank estimate instead of empirical rank selection metrics | rank selection · simulation 2, no offset tensor | rank estimation reliability | Improved |
| add constrained offset tensor to the model | VB-GCP · RSP spike data | held-out performance at low rank | Mixed |
| use negative-binomial GCP instead of Poisson GCP | GCP baseline · RSP spike data | performance | No clear effect |
Closest papers by meaning
- A universal probabilistic spike count model reveals ongoing modulation of neural variability (NeurIPS 2021 · similarity 0.87)
- Conditionally-Conjugate Gaussian Process Factor Analysis for Spike Count Data via Data Augmentation (ICML 2024 · similarity 0.87)
- Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data (ICLR 2024 · similarity 0.86)
- Efficient Nonparametric Tensor Decomposition for Binary and Count Data (AAAI 2024 · similarity 0.85)
- Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors (NeurIPS 2025 · similarity 0.85)
- Learning dynamic representations of the functional connectome in neurobiological networks (ICLR 2024 · similarity 0.85)
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.
