Research map / Learning theory and algorithms / Matrix and tensor methods
Biologically-Plausible Determinant Maximization Neural Networks for Blind Separation of Correlated Sources
Bariscan Bozkurt, Cengiz Pehlevan, Alper Tunga Erdogan
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 WSM instead of NSM | Image separation · Three correlated RGB images | SINR (dB): 17.45 -> 27.49 | Improved |
| Use WSM instead of Infomax ICA | Image separation · Three correlated RGB images | SINR (dB): 13.92 -> 27.49 | Improved |
| Use WSM rather than methods assuming uncorrelated sources | Correlated source separation · Synthetic copula-T sources | SINR | Improved |
| Use online WSM rather than batch Det-Max algorithms | Correlated source separation · Synthetic copula-T sources | SINR | Hurt |
Closest papers by meaning
- Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation (ICLR 2023 · similarity 0.93)
- Normative Networks for Source Separation via Local Plasticity and Dendritic Computation (NeurIPS 2026 · similarity 0.89)
- Range, not Independence, Drives Modularity in Biologically Inspired Representations (ICLR 2025 · similarity 0.81)
- Decomposing stimulus-specific sensory neural information via diffusion models (NeurIPS 2025 · similarity 0.81)
- Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks (NeurIPS 2024 · similarity 0.81)
- Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning (NeurIPS 2024 · similarity 0.81)
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.
