Research map / Probabilistic and scientific modeling / Dynamical systems
Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 correlative (LD) mutual information with source domain constraints instead of ICA independence assumption | BSS of correlated sources · Synthetic antisparse sources, correlation rho up to 0.8 | SINR | Helped |
| Replace batch LD-InfoMax/PMF with online biologically plausible variants | CorInfoMax · Synthetic antisparse sources | SINR | Hurt |
| Source correlation increased (ICA-InfoMax, NSM, BSM assume independent/uncorrelated sources) | ICA-InfoMax, NSM, BSM baselines · Synthetic antisparse sources | SINR | Hurt |
Closest papers by meaning
- 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 0.84)
- Inference with correlated priors using sisters cells (NeurIPS 2025 · similarity 0.83)
- Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning (NeurIPS 2024 · similarity 0.83)
- Decomposing stimulus-specific sensory neural information via diffusion models (NeurIPS 2025 · similarity 0.82)
- What should a neuron aim for? Designing local objective functions based on information theory (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.