AI Paper Atlas

Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes

Deep Random Splines for Point Process Intensity Estimation of Neural Population Data

Gabriel Loaiza-Ganem, Sean Perkins, Karen Schroeder, Mark Churchland, John P. Cunningham

NeurIPS 2019 · Probabilistic and scientific modeling › Uncertainty and Gaussian processes · approach: Infinite-width networks as Gaussian processes · 4 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use DRS-VAE instead of PfLDSPoint-process latent representation and intensity estimation · Simulated dataELBO: 52.3 -> 57.1Improved
Use DRS-VAE instead of PP-GPFAPoint-process latent representation and intensity estimation · Simulated dataL² distance: 15.4 ± 9.64 -> 4.43 ± 3.55Improved
Use DRS-VAE instead of PfLDSPoint-process latent representation and intensity estimation · Reaching data15-NN accuracy: 3.1% -> 23.7%Improved
Use DRS-VAE instead of PfLDSPoint-process latent representation and intensity estimation · Reaching dataELBO: -505.7 -> -500.8Improved
Use DRS-VAE instead of PfLDSPoint-process latent representation and intensity estimation · Cycling dataELBO: 6532 -> 6372Hurt
Use DRS-VAE instead of PfLDSPoint-process latent representation and intensity estimation · Cycling data15-NN accuracy: 11.7% -> 55.9%Improved
Use DRS-VAE instead of PP-GPFAPoint-process latent representation and intensity estimation · Cycling dataSSG/SST: 14.6% -> 70.0%Improved
Use squared splines as nonnegative intensities instead of the constrained spline parameterization (ablation)DRS-VAE · Point-process intensity modelingPerformanceHurt
Use nonnegative-coefficient B-spline basis instead of alternating projections (ablation)DRS-VAE · Point-process intensity modelingPerformanceHurt
Use bidirectional LSTMs instead of regular LSTMs in the encoder (ablation)DRS-VAE · Point-process encoderPerformanceNo clear effect
Increase the number of spline intervals (ablation)DRS-VAE · Cycling dataELBONo clear effect
Increase the number of time bins (ablation)PfLDS · Cycling dataELBO: increased slightlyImproved

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