Unsupervised Learning

Learning that builds a low-dimensional model of input data without error signals or rewards; Hebbian learning is an example.

Neighborhood — ranked by edge-count

paper

framework

Evolutionary Connectionism
implements
Proposed framework translating connectionist learning principles into natural selection domain to explain ETIs.
Connectionist Models
implements
Neural network models demonstrating how organized functional relationships emerge via unsupervised learning; basis for evolutionary connectionism analogy.

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.

Unsupervised learning builds a low-dimensional model of the input data.claim0.831
Clarifies what unsupervised learning does.
Unsupervised Probingmethod0.822
Probing approach avoiding supervision to sidestep complexity-accuracy tradeoff
Supervised Learningframework0.819
Learning through physical changes in mechanical networks, as an example of learning outside neural systems.
Perceptual Learningconcept0.810
Process of inferring causes of sensory information; unified with value learning as integral aspects of free energy minimization.
Learningconcept0.807
Inference of parameters encoding contingencies of the world (e.g., likelihood matrix A) at slower timescale than perception.
Unsupervised Behavior Clusteringmethod0.799
Method that clusters behaviors without prior labels, used to surface concerning learned patterns.
Unsupervised behavior clustering surfaces concerning learned patterns without prior labelsfinding0.794
Empirical finding: unsupervised clustering reveals problematic patterns without needing labeled data.
Associative Learningconcept0.778
Sentience criterion; capacity occurs even in gene regulatory networks and non-neural morphogenetic agents.