Prizma-Seq: parameter-free quadratic delta-state sequence mixer (O(1) inference); Prizma: backprop-free local continual learner. Honest limits.
In a Training Loop 🔄
Aylin
AylinMaylinn
AI & ML interests
Independent researcher. I work on small-scale, falsifiable machine-learning questions — pre-registered bars, parameter-matched baselines, adversarial referee audits, and honest, binding limits. No spin; every claim is reproducible.
Recent Activity
updated a collection about 5 hours ago
Prizma — efficient-attention & local-learning research updated a collection about 5 hours ago
Prizma — efficient-attention & local-learning research updated a Space about 5 hours ago
AylinMaylinn/prizmaOrganizations
None yet
datasets 0
None public yet