SOURCE-LINKED INTELLIGENCE

Memory as transformation: LETHE, a self-referential gan-inspired architecture

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

LETHE (Latent-parameter Evolution with Temporal Hierarchical quasi-Equilibrium) is a self-referential sonic-oblivion system implemented in SuperCollider. It adopts the formal vocabulary of Generative Adversarial Networks in a closed configuration without external datasets or supervision after initialization. Audio is processed by a 3 x 3 mixing matrix built around two delay lines; its nine coefficients and two delay times evolve through the interaction of a five-feature linear discriminator and a random-perturbation optimizer analogous to single-sample REINFORCE. The discriminator compares cur

Read original source ↗ Open in workspace

recordType

paper

region

Global