Enhancing Time Series Forecasting Accuracy by Identifying Optimal Starting Points
Leveraging machine learning techniques to automatically determine the optimal starting point of a time series can significantly enhance the accuracy of time series forecasts.
Time Evidence Fusion Network: A Robust and Efficient Approach to Long-Term Time Series Forecasting
The Time Evidence Fusion Network (TEFN) is a novel neural network architecture that leverages evidence theory and information fusion to achieve robust, efficient, and interpretable long-term time series forecasting.
Minusformer: A Progressive Approach to Enhance Time Series Forecasting by Learning Residuals
The core message of this article is that the proposed Minusformer architecture can effectively mitigate the overfitting problem in time series forecasting by progressively learning the residuals of the supervision signal through a subtraction-based information aggregation mechanism.
The Impact of Source Data Similarity and Diversity on Transfer Learning Performance in Time Series Forecasting
Source data similarity enhances forecasting accuracy and reduces bias, while source diversity enhances forecasting accuracy and uncertainty estimation but increases bias.
Tiny Time Mixers (TTMs): Efficient Pre-trained Models for Improved Zero/Few-Shot Multivariate Time Series Forecasting
Tiny Time Mixers (TTMs), a significantly small pre-trained model (≤1M parameters) based on the lightweight TSMixer architecture, can effectively transfer learning to diverse, unseen target datasets for improved zero/few-shot multivariate time series forecasting.
Delay-Embedding-based Forecast Machine for Accurate Multistep-Ahead Prediction of High-Dimensional Chaotic Systems
The DEFM framework leverages deep neural networks to effectively extract both the spatially and temporally associated information from high-dimensional observed time series, enabling accurate multistep-ahead prediction of the future values of a target variable.
ATFNet: An Adaptive Time-Frequency Ensemble Network for Accurate Long-term Time Series Forecasting
ATFNet is an innovative framework that combines a time domain module and a frequency domain module to concurrently capture local and global dependencies in time series data, with a novel Dominant Harmonic Series Energy Weighting mechanism to dynamically adjust the weights between the two modules based on the periodicity of the input time series.
TEMPO: A Prompt-Based Generative Pre-Trained Transformer for Robust Time Series Forecasting
TEMPO, a novel framework that can effectively learn time series representations by utilizing two essential inductive biases: (i) decomposition of the complex interaction between trend, seasonal and residual components; and (ii) introducing the design of prompts to facilitate distribution adaptation in different types of time series.
Comprehensive and Fair Benchmarking of Time Series Forecasting Methods
The authors propose TFB, an automated benchmark for comprehensive and fair evaluation of time series forecasting methods across diverse datasets and techniques.
S2IP-LLM: Semantic Space Informed Prompt Learning with LLM for Time Series Forecasting
시간 시리즈 예측을 위한 시맨틱 공간 정보 프롬프트 학습의 중요성
© 2024 by Linnk AI