Research map / Probabilistic and scientific modeling / Variational and generative sampling
Continuous multinomial logistic regression for neural decoding
Anuththara Rupasinghe, Jonathan W. Pillow
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 CMLR instead of Naive Bayes | Naive Bayes · Mouse V1 | mean absolute circular error: 4.9 -> 3.1 | Improved |
| use CMLR instead of FlexCode | FlexCode · Mouse V1 | mean absolute circular error: 3.2 -> 3.1 | Mixed |
| use CMLR instead of XGBoost | XGBoost · Mouse V1 | mean absolute circular error: 13.6 -> 3.1 | Improved |
| use CMLR instead of DNN | DNN · Mouse V1 | mean absolute circular error: 18.3 -> 3.1 | Improved |
| use CMLR instead of FlexCode | FlexCode · Mouse hippocampal CA1 | mean Euclidean error: 0.16 -> 0.15 | No clear effect |
| use CMLR instead of XGBoost | XGBoost · Mouse hippocampal CA1 | mean Euclidean error: 0.16 -> 0.15 | No clear effect |
| use CMLR instead of FlexCode | FlexCode · Monkey motor cortex | R2: 0.35 -> 0.53 | Improved |
| use CMLR instead of Naive Bayes | Naive Bayes · Monkey motor cortex | R2: -0.43 -> 0.53 | Improved |
| use DNN instead of CMLR | CMLR · Monkey motor cortex | R2: 0.53 -> 0.58 | Hurt |
| increase number of decoding classes J beyond about 5000 | CMLR · Mouse V1 | mean absolute circular error | No clear effect |
| reduce the number of neurons D or training samples N | CMLR · Mouse V1 scalability | decoding error | No clear effect |
| use CMLR instead of FlexCode for calibration | FlexCode · Mouse V1, macaque V1, mouse CA1 | calibration | Improved |
Closest papers by meaning
- Leveraging unlabelled data for generalizable neural population decoding (NeurIPS 2026 · similarity 0.86)
- Neural Encoding and Decoding at Scale (ICML 2025 · similarity 0.85)
- Divide-and-Conquer Predictive Coding: a structured Bayesian inference algorithm (NeurIPS 2024 · similarity 0.85)
- SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding (NeurIPS 2025 · similarity 0.85)
- Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference (NeurIPS 2025 · similarity 0.84)
- Generalizable, real-time neural decoding with hybrid state-space models (NeurIPS 2025 · similarity 0.84)
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.
