framework
active
framework:universal-darwinism-as-bayesian-inferenceUniversal Darwinism As Bayesian Inference
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Analogy between evolution (model selection) and Bayesian model reduction; but evolution is not curious or insightful
- Variational approach to pattern formation and control in biology (Kuchling et al. 2020).
- The hypothesis that analogous features and circuits reliably form across different neural network models and tasks
- The theory that variation and selection drive evolution; Schrödinger integrates it with quantum theory to explain gene stability.
- The ideal limit of self-supervised learning as modeling the true conditional distribution.
- The stage in the genetic algorithm where top 10% embryos by phenotypic fitness are selected.
- A method for approximate Bayesian inference that optimizes a variational lower bound (ELBO) on log evidence.