Nadezda Alexandrovna Knorozova

2 accepted papers

2024

On the Expressivity of Recurrent Neural Cascades

Nadezda Alexandrovna Knorozova, Alessandro Ronca

AAAI 2024technical

Recurrent Neural Cascades (RNCs) are the recurrent neural networks with no cyclic dependencies among recurrent neurons. This class of recurrent networks has received a lot of attention in practice. Besides training methods for a fixed architecture such as backpropagation, the cascade architecture na…

Cited by 2 Source ↗PDF ↗Scholar ↗

2023

Automata Cascades: Expressivity and Sample Complexity

Alessandro Ronca, Nadezda Alexandrovna Knorozova, Giuseppe De Giacomo

AAAI 2023technical

Every automaton can be decomposed into a cascade of basic prime automata. This is the Prime Decomposition Theorem by Krohn and Rhodes. Guided by this theory, we propose automata cascades as a structured, modular, way to describe automata as complex systems made of many components, each implementing…

Cited by 1 Source ↗PDF ↗Scholar ↗