Representational dynamics

The evolution of an agent's latent representations over the course of training, shown to align with reward improvement when causal emergence is high.

Neighborhood — ranked by edge-count

paper

concept

Causal Emergence
associated_with
Core concept: degree to which an agent exerts unique predictive power on its future; key to cognition at all scales.

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

representational driftconcept0.808
Accumulation of mismatch in later layers causing S degradation.
Representational dynamics aligned with reward improvement in most RL tasks.finding0.804
Secondary empirical result: CE-based representational changes correlate with task success.
Information Dynamicsframework0.802
Proposed theoretical framework combining qualitative and quantitative aspects of information, with explicit treatment of processes and information flow; central organizing concept for the paper.
Structural Representationalismframework0.796
Dominant interpretation of generative models as neural structures with representational content; main target of critique
Representational Transparencyconcept0.792
Property of conscious representations: they do not contain information about the fact that they are representations at the level of the representation itself
Evolutionary dynamicsconcept0.791
The change in genotype/phenotype frequencies over generations under selection, mutation, and development.
Representational Convergenceconcept0.786
The central empirical phenomenon: different neural networks trained on different data/objectives develop increasingly similar representations
Representational Disentanglementconcept0.784
CIMC's characterization of part of the solution to the Hard Problem: insight into the structural necessities of phenomenal representation