framework
active
framework:deep-model-inductionDeep Model Induction
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.
- Links ETIs to the learning of hierarchical representations.
- Hierarchical generative models with separate timescales, enabling long-term planning.
- Prior work on fixed-point convergence in deep networks, foundational to understanding looped model dynamics
- Forward-looking claim connecting toy model findings to large-scale language models
- Generative models that reverse a noising process, mentioned in quasi-simulator table.
- Learning hierarchical representations of non-decomposable functions; proposed as formal equivalent to ETI process.