Research map / Learning theory and algorithms / Prediction and decision losses
A Normative and Biologically Plausible Algorithm for Independent Component Analysis
Yanis Bahroun, Dmitri Chklovskii, Anirvan M. Sengupta
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 the proposed SM-ICA instead of pre-whitening-dependent algorithms on colored data | SM-ICA · Synthetic scenario 2 (colored sub-Gaussian) | source recovery MSE | Improved |
| Use SM-ICA on a mix of sub- and super-Gaussian sources | SM-ICA · Synthetic scenario 3 (white, mixed kurtosis) | source recovery MSE | Improved |
| Use SM-ICA on colored data with mixed kurtosis | SM-ICA · Synthetic scenario 4 | source recovery MSE | Improved |
| Compare SM-ICA with Nonlinear Oja and Amari on white sub-Gaussian data | SM-ICA · Synthetic scenario 1 | convergence speed | No clear effect |
| Use EASI baseline on mixed-kurtosis sources | EASI · Synthetic scenarios 3 and 4 | source recovery | Hurt |
| Use online instead of offline SM-ICA (ablation) | SM-ICA · Speech separation | residual | Hurt |
| Use online instead of offline SM-ICA (ablation) | SM-ICA · Image separation | source recovery | No clear effect |
| Use fixed learning rates instead of time-varying (ablation) | SM-ICA · All tasks | separation quality | No clear effect |
| Apply SM-ICA to speech and image mixtures with no preprocessing change | SM-ICA · Speech (TSP) and natural images | source recovery | Improved |
Closest papers by meaning
- Normative Networks for Source Separation via Local Plasticity and Dendritic Computation (NeurIPS 2026 · similarity 0.86)
- Structured flexibility in recurrent neural networks via neuromodulation (NeurIPS 2024 · similarity 0.84)
- The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks. (ICLR 2024 · similarity 0.84)
- Quasi-Linear ICA for Motor Unit Decomposition during Dynamic Contractions (NeurIPS 2026 · similarity 0.84)
- Improving Deep Learning Speed and Performance Through Synaptic Neural Balance (AAAI 2025 · similarity 0.83)
- NOBLE - Neural Operator with Biologically-informed Latent Embeddings to Capture Experimental Variability in Biological Neuron Models (NeurIPS 2025 · similarity 0.83)
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.
