Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Inzirillo, Hugo"'
Autor:
Genet, Remi, Inzirillo, Hugo
We introduce a new method inspired by Adam that enhances convergence speed and achieves better loss function minima. Traditional optimizers, including Adam, apply uniform or globally adjusted learning rates across neural networks without considering
Externí odkaz:
http://arxiv.org/abs/2410.24216
Autor:
Genet, Remi, Inzirillo, Hugo
Recent research has challenged the necessity of complex deep learning architectures for time series forecasting, demonstrating that simple linear models can often outperform sophisticated approaches. Building upon this insight, we introduce a novel a
Externí odkaz:
http://arxiv.org/abs/2410.21448
Autor:
Inzirillo, Hugo
We propose a new way of building portfolios of cryptocurrencies that provide good diversification properties to investors. First, we seek to filter these digital assets by creating some clusters based on their path signature. The goal is to identify
Externí odkaz:
http://arxiv.org/abs/2410.23297
Autor:
Inzirillo, Hugo, Genet, Remi
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 traditional gating function, aiming to enhance efficiency and interpretabili
Externí odkaz:
http://arxiv.org/abs/2409.15161
Autor:
Inzirillo, Hugo
We explore various neural network architectures for modeling the dynamics of the cryptocurrency market. Traditional linear models often fall short in accurately capturing the unique and complex dynamics of this market. In contrast, Deep Neural Networ
Externí odkaz:
http://arxiv.org/abs/2407.15236
Autor:
Inzirillo, Hugo, Genet, Remi
We propose a novel approach that enhances multivariate function approximation using learnable path signatures and Kolmogorov-Arnold networks (KANs). We enhance the learning capabilities of these networks by weighting the values obtained by KANs using
Externí odkaz:
http://arxiv.org/abs/2406.17890
Autor:
Genet, Remi, Inzirillo, Hugo
Capturing complex temporal patterns and relationships within multivariate data streams is a difficult task. We propose the Temporal Kolmogorov-Arnold Transformer (TKAT), a novel attention-based architecture designed to address this task using Tempora
Externí odkaz:
http://arxiv.org/abs/2406.02486
Autor:
Genet, Remi, Inzirillo, Hugo
Recurrent Neural Networks (RNNs) have revolutionized many areas of machine learning, particularly in natural language and data sequence processing. Long Short-Term Memory (LSTM) has demonstrated its ability to capture long-term dependencies in sequen
Externí odkaz:
http://arxiv.org/abs/2405.07344
It is difficult to identify anomalies in time series, especially when there is a lot of noise. Denoising techniques can remove the noise but this technique can cause a significant loss of information. To detect anomalies in the time series we have pr
Externí odkaz:
http://arxiv.org/abs/2304.10614
Deep learning is playing an increasingly important role in time series analysis. We focused on time series forecasting using attention free mechanism, a more efficient framework, and proposed a new architecture for time series prediction for which li
Externí odkaz:
http://arxiv.org/abs/2209.09548