---
title: TKAN: Temporal Kolmogorov-Arnold Networks
url: https://www.ml-quant.com/papers/ssrn/4825654/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4825654
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4825654
featured: 2024-05-15
citations: 189
topic: Econometrics & Forecasting
---


# TKAN: Temporal Kolmogorov-Arnold Networks

The article presents Temporal Kolomogorov-Arnold Networks (TKANs), a new neural network design that merges the benefits of Recurrent Neural Networks and Long Short-Term Memory for improved multistep time series forecasting.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4825654
- Identifier: SSRN 4825654
- Released: 2024-05-12
- First featured: Quant Letter No. 49 (2024-05-15): https://www.ml-quant.com/issues/2024-05-15/
- Citations (Semantic Scholar): 189
- Published in: not yet
- Topic: Econometrics & Forecasting

## Related

- [Decomposing weather forecasting into advection and convection with neural networks](https://www.ml-quant.com/papers/arxiv/2405.06590/): The research introduces a machine learning model for weather forecasting that separately learns horizontal and vertical atmospheric movements, surpassing existing methods in accuracy and efficiency.
- [Diffusive Gibbs Sampling](https://www.ml-quant.com/papers/arxiv/2402.03008/): The article introduces Diffusive Gibbs Sampling (DiGS), a new method for sampling from multi-modal distributions, which performs better in tasks like Bayesian neural networks and molecular dynamics.
- [Distributional Refinement Network: Distributional Forecasting via Deep Learning](https://www.ml-quant.com/papers/arxiv/2406.00998/): The article introduces the Distributional Refinement Network (DRN), a model that enhances predictive performance and interpretability in actuarial modelling by merging a baseline model with a flexible neural network.
- [Universality of Linear Recurrences Followed by Non-linear Projections: Finite-Width Guarantees and Benefits of Complex Eigenvalues](https://www.ml-quant.com/papers/arxiv/2307.11888/): The study reveals that deep neural networks using linear complex-valued RNNs and MLPs can accurately approximate regular causal sequence-to-sequence maps, with complex eigenvalues near unit disk aiding in information storage.
- [Cross-border Commodity Pricing Strategy Optimization via Mixed Neural Network for Time Series Analysis](https://www.ml-quant.com/papers/arxiv/2408.12115/): The paper presents a new method using the hybrid neural network model CNN-BiGRU-SSA for precise prediction and optimization of cross-border commodity pricing strategies, demonstrating superior performance on various datasets.
- [Amortized Bayesian Multilevel Models](https://www.ml-quant.com/papers/arxiv/2408.13230/): Research explores the use of neural network architectures in Bayesian Multilevel Models to enable efficient training and inference on unseen data sets, solving computational challenges and providing quick posterior inference.