TKAN: Temporal Kolmogorov-Arnold Networks

TL;DR

The paper introduces TKAN, a novel neural network architecture combining Kolmogorov-Arnold Networks and LSTM features, designed for improved multi-step time series forecasting accuracy and efficiency.

Contribution

It proposes the TKAN architecture, integrating RKAN layers with memory management, as a new approach to enhance sequential data modeling beyond traditional RNNs.

Findings

Enhanced multi-step forecasting accuracy

Improved handling of complex sequential patterns

Potential for advancements in time series prediction

Abstract

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 sequential data. Inspired by the Kolmogorov-Arnold Networks (KANs) a promising alternatives to Multi-Layer Perceptrons (MLPs), we proposed a new neural networks architecture inspired by KAN and the LSTM, the Temporal Kolomogorov-Arnold Networks (TKANs). TKANs combined the strenght of both networks, it is composed of Recurring Kolmogorov-Arnold Networks (RKANs) Layers embedding memory management. This innovation enables us to perform multi-step time series forecasting with enhanced accuracy and efficiency. By addressing the limitations of traditional models in handling complex sequential patterns, the TKAN architecture offers significant potential for advancements in fields requiring more than one step ahead forecasting.