Maximum entropy inference on weight distributions under context-dependent task constraints produces neuron populations with contextual gain modulation whose connectivity matches gradient-descent trained networks, with transitions to random structure as context count or weight scale increases.
Flexible Multitask Computation in Recurrent Networks Utilizes Shared Dynamical Motifs
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Introduces finite-lag operator geometry deriving a source-centered transport tensor that decomposes into spread and coherent displacement plus an antisymmetric circulation measure, with proofs of covariance and stability.
citing papers explorer
-
Balancing structure and randomness: maximum entropy networks for context-dependent computations
Maximum entropy inference on weight distributions under context-dependent task constraints produces neuron populations with contextual gain modulation whose connectivity matches gradient-descent trained networks, with transitions to random structure as context count or weight scale increases.
-
Finite-Lag Operator Geometry of Recurrent Representations
Introduces finite-lag operator geometry deriving a source-centered transport tensor that decomposes into spread and coherent displacement plus an antisymmetric circulation measure, with proofs of covariance and stability.