Quantized Approximately Orthogonal Recurrent Neural Networks

no code implementations • 5 Feb 2024 • Armand Foucault, Franck Mamalet, François Malgouyres

Orthogonal recurrent neural networks (ORNNs) are an appealing option for learning tasks involving time series with long-term dependencies, thanks to their simplicity and computational stability.

Quantization Time Series

A general approximation lower bound in $L^p$ norm, with applications to feed-forward neural networks

no code implementations • 9 Jun 2022 • El Mehdi Achour, Armand Foucault, Sébastien Gerchinovitz, François Malgouyres

Given two sets $F$, $G$ of real-valued functions, we first prove a general lower bound on how well functions in $F$ can be approximated in $L^p(\mu)$ norm by functions in $G$, for any $p \geq 1$ and any probability measure $\mu$.

Open-Ended Question Answering