Puls Dane publiczne, aktualizowane automatycznie
arXiv – nowe publikacje publikacja

Differentiable Exact Learning

[Uczenie maszynowe] Autorzy: Hristo Papazov, Francesco D'Angelo, Nicolas Flammarion

We introduce a framework for differentiable exact learning that couples an unbounded external environment to a state-tracking neural controller, which we train on policy-trajectory observations (PTOs): expert behavior traces that expose observations and actions while hiding internal states. In addition to the learning framework, we introduce Differentiable Finite-State Transducers (DFSTs) which use multilinear updates, support log-parallel training, and emulate arbitrary finite-state controllers, yielding computational universality through environmental interaction. From tiny training datasets, compact DFSTs achieve extreme length generalization on arithmetic and universal-simulation tasks. We replicate the success of DFSTs on RNNs and GRUs, thereby supporting a broader learning recipe: State-Tracking Controller + Unbounded External Environment + PTOs = Extreme Length Generalization. Be…

Kategoria arxiv
cs.LG
Kategoria
Uczenie maszynowe
Pdf
https://arxiv.org/pdf/2611.21486v1

Otwórz oryginał w źródle ↗

Więcej z tego źródła

Wszystkie