method
active
method:reversible-residual-network-revnetReversible Residual Network (RevNet)
Bijective invertible architecture used to implement non-linear alignment maps ϕ_nonlin
Neighborhood — ranked by edge-count
Methods (1)
method
- Alignment map implemented as a reversible residual network (RevNet); assumes non-linear representation hypothesis
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.
- Networks with loop connections that can maintain internal state and exhibit dynamical attractors.
- Backbone network pre-trained on ImageNet.
- Novel construct introduced by this paper: a hypothetical graph embedded in the time series of LLM representations, where each dimension is a node and latent connections are edges.
- Emotion feature persistence above and beyond the persistence expected from high variance explained alone, computed by subtracting median variance-matched probe persistence
- Systems of molecular regulation exhibiting associative learning and downward causation; example of misplaced mechanistic assumptions.
- CIMC's current formalization of coherence-maximization as distributed message-passing where processing units negotiate mutual consistency