concept
active
concept:associative-memoryAssociative Memory
Memory system that stores patterns in connection weights and recalls them from partial or noisy cues; property of Hopfield networks and evolved networks
Neighborhood — ranked by edge-count
Findings (1)
finding
- Demonstrates information integration in evolutionary systems with system-level selection
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.
- Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.
- Tuples are referenced by matching typed fields, akin to a relational database.
- Tuple retrieval by matching against a template, similar to relational database queries.
- Learning mechanism: parameter updates resemble classical Hebbian learning with associative and decay terms.
- The central topic, treated as a dynamic, agential process rather than static storage.
- Analytical result showing exponential power activation allows memory storage scaling as 2^(N/2); cited in context of Hopfield scaling.
- Bioelectric pattern memory encoding target morphologies; can be modified by experience and persists across regeneration cycles; functional analog of behavioral memory.