LGMLMar 12, 2020

Time Series Forecasting Using LSTM Networks: A Symbolic Approach

arXiv:2003.05672v1126 citations
AI Analysis

This is an incremental improvement for time series forecasting practitioners, addressing hyperparameter sensitivity and training speed.

The paper tackles the sensitivity and training issues of LSTM networks in time series forecasting by proposing a symbolic representation to reduce dimensions, resulting in faster training without performance loss.

Machine learning methods trained on raw numerical time series data exhibit fundamental limitations such as a high sensitivity to the hyper parameters and even to the initialization of random weights. A combination of a recurrent neural network with a dimension-reducing symbolic representation is proposed and applied for the purpose of time series forecasting. It is shown that the symbolic representation can help to alleviate some of the aforementioned problems and, in addition, might allow for faster training without sacrificing the forecast performance.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes