concept
active
concept:learning-landscapeLearning landscape
The combination of neural weights and SOHMs that defines the brain's learning space.
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Self-Organized Harmonic Modes (SOHMs)associated_withAdam Safron's framework for neural building blocks functioning as symmetry detectors/autoencoders; tanha-free awareness theorized as direct feeling of undoctored SOHMs.
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.
- Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
- The combination of SOHMs and vascular tension that defines the brain's inference process.
- Kauffman's concept of the coupling between an evolving genotype and its fitness landscape as generating internal ordering tendencies in evolution
- Updating the structure of the generative model to better account for observations via Bayesian model reduction and expansion.
- The internalized structure of a living world that becomes part of a person's self-knowledge.
- How well an RL agent learns, measured by reward curves and associated with causal emergence levels.
- Learning paradigm that jointly learns multiple related tasks using a single model
- Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.