10 papers
LEMs: A Primer On Large Execution Models
Remi Genet, Hugo Inzirillo
This paper introduces Large Execution Models (LEMs), a novel deep learning framework that extends transformer-based architectures to address complex execution problems with flexibl…
SigGate: Enhancing Recurrent Neural Networks with Signature-Based Gating Mechanisms
Rémi Genet, Hugo Inzirillo
In this paper, we propose a novel approach that enhances recurrent neural networks (RNNs) by incorporating path signatures into their gating mechanisms. Our method modifies both Lo…
STAN: Smooth Transition Autoregressive Networks
Hugo Inzirillo, Remi Genet
Traditional Smooth Transition Autoregressive (STAR) models offer an effective way to model these dynamics through smooth regime changes based on specific transition variables. In t…
Keras Sig: Efficient Path Signature Computation on GPU in Keras 3
Rémi Genet, Hugo Inzirillo
In this paper we introduce Keras Sig a high-performance pythonic library designed to compute path signature for deep learning applications. Entirely built in Keras 3, \textit{Keras…
A Gated Residual Kolmogorov-Arnold Networks for Mixtures of Experts
Hugo Inzirillo, Remi Genet
This paper introduces KAMoE, a novel Mixture of Experts (MoE) framework based on Gated Residual Kolmogorov-Arnold Networks (GRKAN). We propose GRKAN as an alternative to the tradit…
SigKAN: Signature-Weighted Kolmogorov-Arnold Networks for Time Series
Hugo Inzirillo, Remi Genet
We propose a novel approach that enhances multivariate function approximation using learnable path signatures and Kolmogorov-Arnold networks (KANs). We enhance the learning capabil…