finding
active
finding:bongard-robot-self-modeling-robot-discovers-its-shape-then-reuses-information-after-damageBongard robot self-modeling: robot discovers its shape, then reuses information after damage.
Key Artificial Life experiment illustrating remapping of self-model (Bongard et al. 2006).
Source paper
extracted_from(2024) · Levin, Michael
Neighborhood — ranked by edge-count
Concepts (1)
concept
- remappingassociated_withThe process of reinterpreting and recontextualizing memory engrams for new bodies and environments.
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.
- Evidence for blurring of embodied robot / non-embodied AI distinction through self-modeling
- Robots capable of building internal models of their own body and unexpected changes, blurring the embodied/non-embodied AI distinction
- Antra's foundational claim about how introspection arises computationally rather than from memorised text.
- Foundational claim of the paper, defining self-evidencing.
- The transformer's model of itself as a predictive text engine, developed through in-context learning.
- Claims the model satisfies the core requirements of Mitchell's inductive theory
- Plasticity of the Self is a fundamental property of life.
- Highlights extraordinary plasticity and problem-solving.