Research map / Probabilistic and scientific modeling / Variational and generative sampling
Scalable Spike Source Localization in Extracellular Recordings using Amortized Variational Inference
Cole Hurwitz, Kai Xu, Akash Srivastava, Alessio Buccino, Matthias Hennig
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 |
|---|---|---|---|
| Replace center of mass with VAE model-based localization | Spike localization on square MEA · Simulated square MEA, 10 uV | 2D avg. spike distance from soma: 15.84±10.08 -> 8.79±7.49 (COM 4 ch vs VAE-10 4-9 ch) | Improved |
| Replace center of mass with VAE localization features for GMM spike sorting | Spike sorting on square MEA · Simulated square MEA, all noise levels | precision, recall, accuracy | Improved |
| Add 10uV amplitude jitter averaging to VAE (4-9 channels) (ablation) | VAE · Simulated square MEA, 10 uV | 2D avg. spike distance from soma: 9.21±8.00 -> 8.79±7.49 | Improved |
| Add 10uV amplitude jitter averaging to VAE (9-25 channels) (ablation) | VAE · Simulated square MEA, 10 uV | 2D avg. spike distance from soma: 8.94±7.91 -> 9.12±7.83 | Hurt |
| Use narrower 20um window (4-9 channels) instead of 40um (9-25) (ablation) | VAE · Simulated square MEA | 2D avg. spike distance from soma: 9.12±7.83 -> 8.79±7.49 (10 uV, 10uV jitter) | Improved |
| Use more center-of-mass channels (4 to 25) | Center of mass · Simulated square MEA, 10 uV | 2D avg. spike distance from soma: 15.84±10.08 -> 23.44±14.81 | Hurt |
| Add principal components of waveforms to location features | GMM spike sorting with VAE and COM locations · Simulated square MEA | sorting precision/recall/accuracy | Improved |
| Use VAE trained on a different simulated recording (no retraining) | VAE · Simulated square MEA, 10 uV, new neuron locations | localization and sorting performance | No clear effect |
Closest papers by meaning
- SimSort: A Data-Driven Framework for Spike Sorting by Large-Scale Electrophysiology Simulation (NeurIPS 2025 · similarity 0.85)
- Brain-like Variational Inference (NeurIPS 2025 · similarity 0.85)
- SpikeSSL: A Universal Spike Inference Framework with Dynamics-Informed State-Space Layers (NeurIPS 2026 · similarity 0.84)
- Identifying multi-compartment Hodgkin-Huxley models with high-density extracellular voltage recordings (NeurIPS 2025 · similarity 0.83)
- Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation (NeurIPS 2024 · similarity 0.83)
- P-SPIKESSM: HARNESSING PROBABILISTIC SPIKING STATE SPACE MODELS FOR LONG-RANGE DEPENDENCY TASKS (ICLR 2025 · similarity 0.82)
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.
