Interactive visualizations of classic and modern connectionist models for concept learning, semantic memory, and unsupervised category formation.
Interactive Activation and Competition network — localist semantic memory with bidirectional pool inhibition.
Backprop-trained concept-property semantic memory learning distributed representations.
Vigilance-based clustering on a preset dataset of fruits, blocks, rocks, stars, etc.
Same model, but paste your own CSV data — supports categorical or numeric pool-prefixed columns.
Flat ART with noisy samples + random sensory dropout. A general "fish" hub and species-level hubs emerge without forcing any hierarchy.
Generated dataset of 8 species + 4 generic superordinates (tree, flower, bird, fish), no dropout. The cleanest demonstration that flat ART can recover all 12 prototypes.
Same dataset but with random sensory dropout — pools randomly zeroed out per sample. Demonstrates the model's robustness to missing modalities.
14 prototypes with 2 deliberately corrupted samples per concept mixed in. Templates decay every training step — orphan hubs recruited by garbage samples wither away while the 14 real hubs stay refreshed.