Predictive Entropy Maximization performs competitive blind source separation using only local error-driven and Hebbian updates derived from a surrogate entropy objective with spectral error bounds.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces V-complexity for differentiable functions via piecewise constant approximations, hypothesizes equivalence to RLE and LZ77 compressibility, and applies it to effective complexity in a cream-diffusion model.
citing papers explorer
-
Normative Networks for Source Separation via Local Plasticity and Dendritic Computation
Predictive Entropy Maximization performs competitive blind source separation using only local error-driven and Hebbian updates derived from a surrogate entropy objective with spectral error bounds.
-
The information-theoretic complexity of differentiable functions
Introduces V-complexity for differentiable functions via piecewise constant approximations, hypothesizes equivalence to RLE and LZ77 compressibility, and applies it to effective complexity in a cream-diffusion model.