Discussing the article: "Neural Networks Made Easy (Part 87): Time Series Patching"

[MetaQuotes]

Check out the new article: Neural Networks Made Easy (Part 87): Time Series Patching.

Forecasting plays an important role in time series analysis. In the new article, we will talk about the benefits of time series patching.

The Transformer architecture, which originated in the field of natural language processing (NLP), demonstrated its advantages in computer vision (CV) and is successfully applied in time series analysis. Its Self-Attention mechanism, which can automatically identify relationships between elements of a time series, has become the basis for creating effective forecasting models.

As the volume of data available for analysis grows and machine learning methods improve, it becomes possible to develop more accurate and efficient models for analyzing time data. However, as the complexity of time series increases, we need to develop more efficient and less costly analysis methods to achieve accurate forecasts and identify hidden patterns.

One of such methods is Patch Time Series Transformer, PatchTST, which was presented in the article "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers". This method is based on dividing time series into segments (patches) and using Transformer to predict future values.

Author: Dmitriy Gizlyk

[Timothy Walshak]

I have been following the series for a while now, and it has be  insightful.

I have one question however; will the entire series be published as a book at the end?

[Liliya Yunusova]

Timothy Walshak #:

I have been following the series for a while now, and it has be  insightful.

I have one question however; will the entire series be published as a book at the end?

Hi,

Dmitriy Gizlyk, the author of this series, has already written a book on neural networks in trading. You can find it here: https://www.mql5.com/en/neurobook. Feel free to download it in pdf or chm.