Artificial Intelligence - page 3

[Sergey Golubev]

Forum on trading, automated trading systems and testing trading strategies

The Ultimate AI EA Project

Sergey Golubev, 2026.06.08 13:36

Neural Networks in Trading: Anomaly Detection in the Frequency Domain (Final Part)

In the previous article, we introduced the innovative CATCH framework for anomaly detection in multivariate time series. The frequency-domain analysis method proposed by the framework's authors enables not only the detection of point anomalies such as outliers and abrupt changes, but also the identification of more complex hidden patterns that often evade traditional approaches. The CATCH framework employs the Fourier transform to convert data from the time domain into its spectral representation, opening new opportunities for a detailed analysis of the characteristics of the sequence under examination.

[Sergey Golubev]

Forum on trading, automated trading systems and testing trading strategies

The Ultimate AI EA Project

Sergey Golubev, 2026.06.09 14:11

Neural Networks in Trading: Hierarchical Skill Discovery for Adaptive Agent Behavior (HiSSD)

The core idea behind HiSSD is simultaneous hierarchical learning. This approach provides a deeper understanding of both the temporal aspects of interactions and the context of specific tasks. As a result, it not only improves the quality of agent behavior but also facilitates reliable transfer of learned strategies to new environments.